ros/claude-task-master
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Implement MCP (#20)

Browse Source
This commit is contained in:
Ralph Khreish
2025-03-28 20:38:53 +01:00
committed by GitHub
parent 98d5cefba8
commit 4eed269378
23 changed files with 3795 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

107
.changeset/README.md Normal file
View File

@@ -0,0 +1,107 @@
# Changesets
This folder has been automatically generated by `@changesets/cli`, a build tool that works with multi-package repos or single-package repos to help version and publish code. Full documentation is available in the [Changesets repository](https://github.com/changesets/changesets).
## What are Changesets?
Changesets are a way to track changes to packages in your repository. Each changeset:
- Describes the changes you've made
- Specifies the type of version bump needed (patch, minor, or major)
- Connects these changes with release notes
- Automates the versioning and publishing process
## How to Use Changesets in Task Master
### 2. Making Changes
1. Create a new branch for your changes
2. Make your code changes
3. Write tests and ensure all tests pass
### 3. Creating a Changeset
After making changes, create a changeset by running:
```bash
npx changeset
```
This will:
- Walk you through a CLI to describe your changes
- Ask you to select impact level (patch, minor, major)
- Create a markdown file in the `.changeset` directory
### 4. Impact Level Guidelines
When choosing the impact level for your changes:
- **Patch**: Bug fixes and minor changes that don't affect how users interact with the system
- Example: Fixing a typo in output text, optimizing code without changing behavior
- **Minor**: New features or enhancements that don't break existing functionality
- Example: Adding a new flag to an existing command, adding new task metadata fields
- **Major**: Breaking changes that require users to update their usage
- Example: Renaming a command, changing the format of the tasks.json file
### 5. Writing Good Changeset Descriptions
Your changeset description should:
- Be written for end-users, not developers
- Clearly explain what changed and why
- Include any migration steps or backward compatibility notes
- Reference related issues or pull requests with `#issue-number`
Examples:
```md
# Good
Added new `--research` flag to the `expand` command that uses Perplexity AI
to provide research-backed task expansions. Requires PERPLEXITY_API_KEY
environment variable.
# Not Good
Fixed stuff and added new flag
```
### 6. Committing Your Changes
Commit both your code changes and the generated changeset file:
```bash
git add .
git commit -m "Add feature X with changeset"
git push
```
### 7. Pull Request Process
1. Open a pull request
2. Ensure CI passes
3. Await code review
4. Once approved and merged, your changeset will be used during the next release
## Release Process (for Maintainers)
When it's time to make a release:
1. Ensure all desired changesets are merged
2. Run `npx changeset version` to update package versions and changelog
3. Review and commit the changes
4. Run `npm publish` to publish to npm
This can be automated through Github Actions
## Common Issues and Solutions
- **Merge Conflicts in Changeset Files**: Resolve just like any other merge conflict
- **Multiple Changes in One PR**: Create multiple changesets if changes affect different areas
- **Accidentally Committed Without Changeset**: Create the changeset after the fact and commit it separately
## Additional Resources
- [Changesets Documentation](https://github.com/changesets/changesets)
- [Common Questions](https://github.com/changesets/changesets/blob/main/docs/common-questions.md)

14
.changeset/config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"$schema": "https://unpkg.com/@changesets/config@3.1.1/schema.json",
"changelog": [
"@changesets/changelog-github",
{ "repo": "eyaltoledano/claude-task-master" }
],
"commit": false,
"fixed": [],
"linked": [],
"access": "restricted",
"baseBranch": "main",
"updateInternalDependencies": "patch",
"ignore": []
}

5
.changeset/flat-candies-wonder.md Normal file
View File

@@ -0,0 +1,5 @@
---
"task-master-ai": patch
---
Added changeset config #39

5
.changeset/nice-cougars-itch.md Normal file
View File

@@ -0,0 +1,5 @@
---
"task-master-ai": minor
---
add github actions to automate github and npm releases

5
.changeset/odd-weeks-melt.md Normal file
View File

@@ -0,0 +1,5 @@
---
"task-master-ai": minor
---
Implement MCP server for all commands using tools.

28
.github/release.yml vendored Normal file
View File

@@ -0,0 +1,28 @@
name: Release
on:
push:
branches:
- main
- next
jobs:
release:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- uses: actions/setup-node@v4
with:
node-version: 18
- name: Install Dependencies
run: npm install
- name: Create Release Pull Request or Publish to npm
uses: changesets/action@1.4.10
with:
publish: npm run release
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}

64
README-task-master.md
View File

@@ -1,4 +1,5 @@
# Task Master
### by [@eyaltoledano](https://x.com/eyaltoledano)
A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI.
@@ -15,9 +16,11 @@ A task management system for AI-driven development with Claude, designed to work
The script can be configured through environment variables in a `.env` file at the root of the project:
### Required Configuration
- `ANTHROPIC_API_KEY`: Your Anthropic API key for Claude
### Optional Configuration
- `MODEL`: Specify which Claude model to use (default: "claude-3-7-sonnet-20250219")
- `MAX_TOKENS`: Maximum tokens for model responses (default: 4000)
- `TEMPERATURE`: Temperature for model responses (default: 0.7)
@@ -123,6 +126,21 @@ Claude Task Master is designed to work seamlessly with [Cursor AI](https://www.c
3. Place your PRD document in the `scripts/` directory (e.g., `scripts/prd.txt`)
4. Open Cursor's AI chat and switch to Agent mode
### Setting up MCP in Cursor
To enable enhanced task management capabilities directly within Cursor using the Model Control Protocol (MCP):
1. Go to Cursor settings
2. Navigate to the MCP section
3. Click on "Add New MCP Server"
4. Configure with the following details:
- Name: "Task Master"
- Type: "Command"
- Command: "npx -y --package task-master-ai task-master-mcp"
5. Save the settings
Once configured, you can interact with Task Master's task management commands directly through Cursor's interface, providing a more integrated experience.
### Initial Task Generation
In Cursor's AI chat, instruct the agent to generate tasks from your PRD:
@@ -132,11 +150,13 @@ Please use the task-master parse-prd command to generate tasks from my PRD. The
```
The agent will execute:
```bash
task-master parse-prd scripts/prd.txt
```
This will:
- Parse your PRD document
- Generate a structured `tasks.json` file with tasks, dependencies, priorities, and test strategies
- The agent will understand this process due to the Cursor rules
@@ -150,6 +170,7 @@ Please generate individual task files from tasks.json
```
The agent will execute:
```bash
task-master generate
```
@@ -169,6 +190,7 @@ What tasks are available to work on next?
```
The agent will:
- Run `task-master list` to see all tasks
- Run `task-master next` to determine the next task to work on
- Analyze dependencies to determine which tasks are ready to be worked on
@@ -178,12 +200,14 @@ The agent will:
### 2. Task Implementation
When implementing a task, the agent will:
- Reference the task's details section for implementation specifics
- Consider dependencies on previous tasks
- Follow the project's coding standards
- Create appropriate tests based on the task's testStrategy
You can ask:
```
Let's implement task 3. What does it involve?
```
@@ -191,6 +215,7 @@ Let's implement task 3. What does it involve?
### 3. Task Verification
Before marking a task as complete, verify it according to:
- The task's specified testStrategy
- Any automated tests in the codebase
- Manual verification if required
@@ -204,6 +229,7 @@ Task 3 is now complete. Please update its status.
```
The agent will execute:
```bash
task-master set-status --id=3 --status=done
```
@@ -211,16 +237,19 @@ task-master set-status --id=3 --status=done
### 5. Handling Implementation Drift
If during implementation, you discover that:
- The current approach differs significantly from what was planned
- Future tasks need to be modified due to current implementation choices
- New dependencies or requirements have emerged
Tell the agent:
```
We've changed our approach. We're now using Express instead of Fastify. Please update all future tasks to reflect this change.
```
The agent will execute:
```bash
task-master update --from=4 --prompt="Now we are using Express instead of Fastify."
```
@@ -236,36 +265,43 @@ Task 5 seems complex. Can you break it down into subtasks?
```
The agent will execute:
```bash
task-master expand --id=5 --num=3
```
You can provide additional context:
```
Please break down task 5 with a focus on security considerations.
```
The agent will execute:
```bash
task-master expand --id=5 --prompt="Focus on security aspects"
```
You can also expand all pending tasks:
```
Please break down all pending tasks into subtasks.
```
The agent will execute:
```bash
task-master expand --all
```
For research-backed subtask generation using Perplexity AI:
```
Please break down task 5 using research-backed generation.
```
The agent will execute:
```bash
task-master expand --id=5 --research
```
@@ -275,6 +311,7 @@ task-master expand --id=5 --research
Here's a comprehensive reference of all available commands:
### Parse PRD
```bash
# Parse a PRD file and generate tasks
task-master parse-prd <prd-file.txt>
@@ -284,6 +321,7 @@ task-master parse-prd <prd-file.txt> --num-tasks=10
```
### List Tasks
```bash
# List all tasks
task-master list
@@ -299,12 +337,14 @@ task-master list --status=<status> --with-subtasks
```
### Show Next Task
```bash
# Show the next task to work on based on dependencies and status
task-master next
```
### Show Specific Task
```bash
# Show details of a specific task
task-master show <id>
@@ -316,18 +356,21 @@ task-master show 1.2
```
### Update Tasks
```bash
# Update tasks from a specific ID and provide context
task-master update --from=<id> --prompt="<prompt>"
```
### Generate Task Files
```bash
# Generate individual task files from tasks.json
task-master generate
```
### Set Task Status
```bash
# Set status of a single task
task-master set-status --id=<id> --status=<status>
@@ -342,6 +385,7 @@ task-master set-status --id=1.1,1.2 --status=<status>
When marking a task as "done", all of its subtasks will automatically be marked as "done" as well.
### Expand Tasks
```bash
# Expand a specific task with subtasks
task-master expand --id=<id> --num=<number>
@@ -363,6 +407,7 @@ task-master expand --all --research
```
### Clear Subtasks
```bash
# Clear subtasks from a specific task
task-master clear-subtasks --id=<id>
@@ -375,6 +420,7 @@ task-master clear-subtasks --all
```
### Analyze Task Complexity
```bash
# Analyze complexity of all tasks
task-master analyze-complexity
@@ -396,6 +442,7 @@ task-master analyze-complexity --research
```
### View Complexity Report
```bash
# Display the task complexity analysis report
task-master complexity-report
@@ -405,6 +452,7 @@ task-master complexity-report --file=my-report.json
```
### Managing Task Dependencies
```bash
# Add a dependency to a task
task-master add-dependency --id=<id> --depends-on=<id>
@@ -420,6 +468,7 @@ task-master fix-dependencies
```
### Add a New Task
```bash
# Add a new task using AI
task-master add-task --prompt="Description of the new task"
@@ -436,6 +485,7 @@ task-master add-task --prompt="Description" --priority=high
### Analyzing Task Complexity
The `analyze-complexity` command:
- Analyzes each task using AI to assess its complexity on a scale of 1-10
- Recommends optimal number of subtasks based on configured DEFAULT_SUBTASKS
- Generates tailored prompts for expanding each task
@@ -443,6 +493,7 @@ The `analyze-complexity` command:
- Saves the report to scripts/task-complexity-report.json by default
The generated report contains:
- Complexity analysis for each task (scored 1-10)
- Recommended number of subtasks based on complexity
- AI-generated expansion prompts customized for each task
@@ -451,6 +502,7 @@ The generated report contains:
### Viewing Complexity Report
The `complexity-report` command:
- Displays a formatted, easy-to-read version of the complexity analysis report
- Shows tasks organized by complexity score (highest to lowest)
- Provides complexity distribution statistics (low, medium, high)
@@ -463,12 +515,14 @@ The `complexity-report` command:
The `expand` command automatically checks for and uses the complexity report:
When a complexity report exists:
- Tasks are automatically expanded using the recommended subtask count and prompts
- When expanding all tasks, they're processed in order of complexity (highest first)
- Research-backed generation is preserved from the complexity analysis
- You can still override recommendations with explicit command-line options
Example workflow:
```bash
# Generate the complexity analysis report with research capabilities
task-master analyze-complexity --research
@@ -485,6 +539,7 @@ task-master expand --all
### Finding the Next Task
The `next` command:
- Identifies tasks that are pending/in-progress and have all dependencies satisfied
- Prioritizes tasks by priority level, dependency count, and task ID
- Displays comprehensive information about the selected task:
@@ -499,6 +554,7 @@ The `next` command:
### Viewing Specific Task Details
The `show` command:
- Displays comprehensive details about a specific task or subtask
- Shows task status, priority, dependencies, and detailed implementation notes
- For parent tasks, displays all subtasks and their status
@@ -529,43 +585,51 @@ The `show` command:
## Example Cursor AI Interactions
### Starting a new project
```
I've just initialized a new project with Claude Task Master. I have a PRD at scripts/prd.txt.
Can you help me parse it and set up the initial tasks?
```
### Working on tasks
```
What's the next task I should work on? Please consider dependencies and priorities.
```
### Implementing a specific task
```
I'd like to implement task 4. Can you help me understand what needs to be done and how to approach it?
```
### Managing subtasks
```
I need to regenerate the subtasks for task 3 with a different approach. Can you help me clear and regenerate them?
```
### Handling changes
```
We've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks to reflect this change?
```
### Completing work
```
I've finished implementing the authentication system described in task 2. All tests are passing.
Please mark it as complete and tell me what I should work on next.
```
### Analyzing complexity
```
Can you analyze the complexity of our tasks to help me understand which ones need to be broken down further?
```
### Viewing complexity report
```
Can you show me the complexity report in a more readable format?
```

99
README.md
View File

@@ -1,4 +1,5 @@
# Task Master
### by [@eyaltoledano](https://x.com/eyaltoledano)
A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI.
@@ -15,9 +16,11 @@ A task management system for AI-driven development with Claude, designed to work
The script can be configured through environment variables in a `.env` file at the root of the project:
### Required Configuration
- `ANTHROPIC_API_KEY`: Your Anthropic API key for Claude
### Optional Configuration
- `MODEL`: Specify which Claude model to use (default: "claude-3-7-sonnet-20250219")
- `MAX_TOKENS`: Maximum tokens for model responses (default: 4000)
- `TEMPERATURE`: Temperature for model responses (default: 0.7)
@@ -123,6 +126,21 @@ Claude Task Master is designed to work seamlessly with [Cursor AI](https://www.c
3. Place your PRD document in the `scripts/` directory (e.g., `scripts/prd.txt`)
4. Open Cursor's AI chat and switch to Agent mode
### Setting up MCP in Cursor
To enable enhanced task management capabilities directly within Cursor using the Model Control Protocol (MCP):
1. Go to Cursor settings
2. Navigate to the MCP section
3. Click on "Add New MCP Server"
4. Configure with the following details:
- Name: "Task Master"
- Type: "Command"
- Command: "npx -y --package task-master-ai task-master-mcp"
5. Save the settings
Once configured, you can interact with Task Master's task management commands directly through Cursor's interface, providing a more integrated experience.
### Initial Task Generation
In Cursor's AI chat, instruct the agent to generate tasks from your PRD:
@@ -132,11 +150,13 @@ Please use the task-master parse-prd command to generate tasks from my PRD. The
```
The agent will execute:
```bash
task-master parse-prd scripts/prd.txt
```
This will:
- Parse your PRD document
- Generate a structured `tasks.json` file with tasks, dependencies, priorities, and test strategies
- The agent will understand this process due to the Cursor rules
@@ -150,6 +170,7 @@ Please generate individual task files from tasks.json
```
The agent will execute:
```bash
task-master generate
```
@@ -169,6 +190,7 @@ What tasks are available to work on next?
```
The agent will:
- Run `task-master list` to see all tasks
- Run `task-master next` to determine the next task to work on
- Analyze dependencies to determine which tasks are ready to be worked on
@@ -178,12 +200,14 @@ The agent will:
### 2. Task Implementation
When implementing a task, the agent will:
- Reference the task's details section for implementation specifics
- Consider dependencies on previous tasks
- Follow the project's coding standards
- Create appropriate tests based on the task's testStrategy
You can ask:
```
Let's implement task 3. What does it involve?
```
@@ -191,6 +215,7 @@ Let's implement task 3. What does it involve?
### 3. Task Verification
Before marking a task as complete, verify it according to:
- The task's specified testStrategy
- Any automated tests in the codebase
- Manual verification if required
@@ -204,6 +229,7 @@ Task 3 is now complete. Please update its status.
```
The agent will execute:
```bash
task-master set-status --id=3 --status=done
```
@@ -211,16 +237,19 @@ task-master set-status --id=3 --status=done
### 5. Handling Implementation Drift
If during implementation, you discover that:
- The current approach differs significantly from what was planned
- Future tasks need to be modified due to current implementation choices
- New dependencies or requirements have emerged
Tell the agent:
```
We've changed our approach. We're now using Express instead of Fastify. Please update all future tasks to reflect this change.
```
The agent will execute:
```bash
task-master update --from=4 --prompt="Now we are using Express instead of Fastify."
```
@@ -236,36 +265,43 @@ Task 5 seems complex. Can you break it down into subtasks?
```
The agent will execute:
```bash
task-master expand --id=5 --num=3
```
You can provide additional context:
```
Please break down task 5 with a focus on security considerations.
```
The agent will execute:
```bash
task-master expand --id=5 --prompt="Focus on security aspects"
```
You can also expand all pending tasks:
```
Please break down all pending tasks into subtasks.
```
The agent will execute:
```bash
task-master expand --all
```
For research-backed subtask generation using Perplexity AI:
```
Please break down task 5 using research-backed generation.
```
The agent will execute:
```bash
task-master expand --id=5 --research
```
@@ -275,6 +311,7 @@ task-master expand --id=5 --research
Here's a comprehensive reference of all available commands:
### Parse PRD
```bash
# Parse a PRD file and generate tasks
task-master parse-prd <prd-file.txt>
@@ -284,6 +321,7 @@ task-master parse-prd <prd-file.txt> --num-tasks=10
```
### List Tasks
```bash
# List all tasks
task-master list
@@ -299,12 +337,14 @@ task-master list --status=<status> --with-subtasks
```
### Show Next Task
```bash
# Show the next task to work on based on dependencies and status
task-master next
```
### Show Specific Task
```bash
# Show details of a specific task
task-master show <id>
@@ -316,18 +356,21 @@ task-master show 1.2
```
### Update Tasks
```bash
# Update tasks from a specific ID and provide context
task-master update --from=<id> --prompt="<prompt>"
```
### Generate Task Files
```bash
# Generate individual task files from tasks.json
task-master generate
```
### Set Task Status
```bash
# Set status of a single task
task-master set-status --id=<id> --status=<status>
@@ -342,6 +385,7 @@ task-master set-status --id=1.1,1.2 --status=<status>
When marking a task as "done", all of its subtasks will automatically be marked as "done" as well.
### Expand Tasks
```bash
# Expand a specific task with subtasks
task-master expand --id=<id> --num=<number>
@@ -363,6 +407,7 @@ task-master expand --all --research
```
### Clear Subtasks
```bash
# Clear subtasks from a specific task
task-master clear-subtasks --id=<id>
@@ -375,6 +420,7 @@ task-master clear-subtasks --all
```
### Analyze Task Complexity
```bash
# Analyze complexity of all tasks
task-master analyze-complexity
@@ -396,6 +442,7 @@ task-master analyze-complexity --research
```
### View Complexity Report
```bash
# Display the task complexity analysis report
task-master complexity-report
@@ -405,6 +452,7 @@ task-master complexity-report --file=my-report.json
```
### Managing Task Dependencies
```bash
# Add a dependency to a task
task-master add-dependency --id=<id> --depends-on=<id>
@@ -420,7 +468,8 @@ task-master fix-dependencies
```
### Add a New Task
```bash
````bash
# Add a new task using AI
task-master add-task --prompt="Description of the new task"
@@ -468,7 +517,7 @@ npm install -g task-master-ai
# OR install locally within your project
npm install task-master-ai
```
````
### Initialize a new project
@@ -562,11 +611,13 @@ Please use the task-master parse-prd command to generate tasks from my PRD. The
```
The agent will execute:
```bash
task-master parse-prd scripts/prd.txt
```
This will:
- Parse your PRD document
- Generate a structured `tasks.json` file with tasks, dependencies, priorities, and test strategies
- The agent will understand this process due to the Cursor rules
@@ -580,6 +631,7 @@ Please generate individual task files from tasks.json
```
The agent will execute:
```bash
task-master generate
```
@@ -599,6 +651,7 @@ What tasks are available to work on next?
```
The agent will:
- Run `task-master list` to see all tasks
- Run `task-master next` to determine the next task to work on
- Analyze dependencies to determine which tasks are ready to be worked on
@@ -608,12 +661,14 @@ The agent will:
### 2. Task Implementation
When implementing a task, the agent will:
- Reference the task's details section for implementation specifics
- Consider dependencies on previous tasks
- Follow the project's coding standards
- Create appropriate tests based on the task's testStrategy
You can ask:
```
Let's implement task 3. What does it involve?
```
@@ -621,6 +676,7 @@ Let's implement task 3. What does it involve?
### 3. Task Verification
Before marking a task as complete, verify it according to:
- The task's specified testStrategy
- Any automated tests in the codebase
- Manual verification if required
@@ -634,6 +690,7 @@ Task 3 is now complete. Please update its status.
```
The agent will execute:
```bash
task-master set-status --id=3 --status=done
```
@@ -641,16 +698,19 @@ task-master set-status --id=3 --status=done
### 5. Handling Implementation Drift
If during implementation, you discover that:
- The current approach differs significantly from what was planned
- Future tasks need to be modified due to current implementation choices
- New dependencies or requirements have emerged
Tell the agent:
```
We've changed our approach. We're now using Express instead of Fastify. Please update all future tasks to reflect this change.
```
The agent will execute:
```bash
task-master update --from=4 --prompt="Now we are using Express instead of Fastify."
```
@@ -666,36 +726,43 @@ Task 5 seems complex. Can you break it down into subtasks?
```
The agent will execute:
```bash
task-master expand --id=5 --num=3
```
You can provide additional context:
```
Please break down task 5 with a focus on security considerations.
```
The agent will execute:
```bash
task-master expand --id=5 --prompt="Focus on security aspects"
```
You can also expand all pending tasks:
```
Please break down all pending tasks into subtasks.
```
The agent will execute:
```bash
task-master expand --all
```
For research-backed subtask generation using Perplexity AI:
```
Please break down task 5 using research-backed generation.
```
The agent will execute:
```bash
task-master expand --id=5 --research
```
@@ -705,6 +772,7 @@ task-master expand --id=5 --research
Here's a comprehensive reference of all available commands:
### Parse PRD
```bash
# Parse a PRD file and generate tasks
task-master parse-prd <prd-file.txt>
@@ -714,6 +782,7 @@ task-master parse-prd <prd-file.txt> --num-tasks=10
```
### List Tasks
```bash
# List all tasks
task-master list
@@ -729,12 +798,14 @@ task-master list --status=<status> --with-subtasks
```
### Show Next Task
```bash
# Show the next task to work on based on dependencies and status
task-master next
```
### Show Specific Task
```bash
# Show details of a specific task
task-master show <id>
@@ -746,18 +817,21 @@ task-master show 1.2
```
### Update Tasks
```bash
# Update tasks from a specific ID and provide context
task-master update --from=<id> --prompt="<prompt>"
```
### Generate Task Files
```bash
# Generate individual task files from tasks.json
task-master generate
```
### Set Task Status
```bash
# Set status of a single task
task-master set-status --id=<id> --status=<status>
@@ -772,6 +846,7 @@ task-master set-status --id=1.1,1.2 --status=<status>
When marking a task as "done", all of its subtasks will automatically be marked as "done" as well.
### Expand Tasks
```bash
# Expand a specific task with subtasks
task-master expand --id=<id> --num=<number>
@@ -793,6 +868,7 @@ task-master expand --all --research
```
### Clear Subtasks
```bash
# Clear subtasks from a specific task
task-master clear-subtasks --id=<id>
@@ -805,6 +881,7 @@ task-master clear-subtasks --all
```
### Analyze Task Complexity
```bash
# Analyze complexity of all tasks
task-master analyze-complexity
@@ -826,6 +903,7 @@ task-master analyze-complexity --research
```
### View Complexity Report
```bash
# Display the task complexity analysis report
task-master complexity-report
@@ -835,6 +913,7 @@ task-master complexity-report --file=my-report.json
```
### Managing Task Dependencies
```bash
# Add a dependency to a task
task-master add-dependency --id=<id> --depends-on=<id>
@@ -850,6 +929,7 @@ task-master fix-dependencies
```
### Add a New Task
```bash
# Add a new task using AI
task-master add-task --prompt="Description of the new task"
@@ -866,6 +946,7 @@ task-master add-task --prompt="Description" --priority=high
### Analyzing Task Complexity
The `analyze-complexity` command:
- Analyzes each task using AI to assess its complexity on a scale of 1-10
- Recommends optimal number of subtasks based on configured DEFAULT_SUBTASKS
- Generates tailored prompts for expanding each task
@@ -873,6 +954,7 @@ The `analyze-complexity` command:
- Saves the report to scripts/task-complexity-report.json by default
The generated report contains:
- Complexity analysis for each task (scored 1-10)
- Recommended number of subtasks based on complexity
- AI-generated expansion prompts customized for each task
@@ -881,6 +963,7 @@ The generated report contains:
### Viewing Complexity Report
The `complexity-report` command:
- Displays a formatted, easy-to-read version of the complexity analysis report
- Shows tasks organized by complexity score (highest to lowest)
- Provides complexity distribution statistics (low, medium, high)
@@ -893,12 +976,14 @@ The `complexity-report` command:
The `expand` command automatically checks for and uses the complexity report:
When a complexity report exists:
- Tasks are automatically expanded using the recommended subtask count and prompts
- When expanding all tasks, they're processed in order of complexity (highest first)
- Research-backed generation is preserved from the complexity analysis
- You can still override recommendations with explicit command-line options
Example workflow:
```bash
# Generate the complexity analysis report with research capabilities
task-master analyze-complexity --research
@@ -915,6 +1000,7 @@ task-master expand --all
### Finding the Next Task
The `next` command:
- Identifies tasks that are pending/in-progress and have all dependencies satisfied
- Prioritizes tasks by priority level, dependency count, and task ID
- Displays comprehensive information about the selected task:
@@ -929,6 +1015,7 @@ The `next` command:
### Viewing Specific Task Details
The `show` command:
- Displays comprehensive details about a specific task or subtask
- Shows task status, priority, dependencies, and detailed implementation notes
- For parent tasks, displays all subtasks and their status
@@ -959,43 +1046,51 @@ The `show` command:
## Example Cursor AI Interactions
### Starting a new project
```
I've just initialized a new project with Claude Task Master. I have a PRD at scripts/prd.txt.
Can you help me parse it and set up the initial tasks?
```
### Working on tasks
```
What's the next task I should work on? Please consider dependencies and priorities.
```
### Implementing a specific task
```
I'd like to implement task 4. Can you help me understand what needs to be done and how to approach it?
```
### Managing subtasks
```
I need to regenerate the subtasks for task 3 with a different approach. Can you help me clear and regenerate them?
```
### Handling changes
```
We've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks to reflect this change?
```
### Completing work
```
I've finished implementing the authentication system described in task 2. All tests are passing.
Please mark it as complete and tell me what I should work on next.
```
### Analyzing complexity
```
Can you analyze the complexity of our tasks to help me understand which ones need to be broken down further?
```
### Viewing complexity report
```
Can you show me the complexity report in a more readable format?
```

36
mcp-server/server.js Executable file
View File

@@ -0,0 +1,36 @@
#!/usr/bin/env node
import TaskMasterMCPServer from "./src/index.js";
import dotenv from "dotenv";
import logger from "./src/logger.js";
// Load environment variables
dotenv.config();
/**
* Start the MCP server
*/
async function startServer() {
const server = new TaskMasterMCPServer();
// Handle graceful shutdown
process.on("SIGINT", async () => {
await server.stop();
process.exit(0);
});
process.on("SIGTERM", async () => {
await server.stop();
process.exit(0);
});
try {
await server.start();
} catch (error) {
logger.error(`Failed to start MCP server: ${error.message}`);
process.exit(1);
}
}
// Start the server
startServer();

86
mcp-server/src/index.js Normal file
View File

@@ -0,0 +1,86 @@
import { FastMCP } from "fastmcp";
import path from "path";
import dotenv from "dotenv";
import { fileURLToPath } from "url";
import fs from "fs";
import logger from "./logger.js";
import { registerTaskMasterTools } from "./tools/index.js";
// Load environment variables
dotenv.config();
// Constants
const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);
/**
* Main MCP server class that integrates with Task Master
*/
class TaskMasterMCPServer {
constructor() {
// Get version from package.json using synchronous fs
const packagePath = path.join(__dirname, "../../package.json");
const packageJson = JSON.parse(fs.readFileSync(packagePath, "utf8"));
this.options = {
name: "Task Master MCP Server",
version: packageJson.version,
};
this.server = new FastMCP(this.options);
this.initialized = false;
// this.server.addResource({});
// this.server.addResourceTemplate({});
// Bind methods
this.init = this.init.bind(this);
this.start = this.start.bind(this);
this.stop = this.stop.bind(this);
// Setup logging
this.logger = logger;
}
/**
* Initialize the MCP server with necessary tools and routes
*/
async init() {
if (this.initialized) return;
// Register Task Master tools
registerTaskMasterTools(this.server);
this.initialized = true;
return this;
}
/**
* Start the MCP server
*/
async start() {
if (!this.initialized) {
await this.init();
}
// Start the FastMCP server
await this.server.start({
transportType: "stdio",
});
return this;
}
/**
* Stop the MCP server
*/
async stop() {
if (this.server) {
await this.server.stop();
}
}
}
export default TaskMasterMCPServer;

68
mcp-server/src/logger.js Normal file
View File

@@ -0,0 +1,68 @@
import chalk from "chalk";
// Define log levels
const LOG_LEVELS = {
debug: 0,
info: 1,
warn: 2,
error: 3,
success: 4,
};
// Get log level from environment or default to info
const LOG_LEVEL = process.env.LOG_LEVEL
? LOG_LEVELS[process.env.LOG_LEVEL.toLowerCase()]
: LOG_LEVELS.info;
/**
* Logs a message with the specified level
* @param {string} level - The log level (debug, info, warn, error, success)
* @param {...any} args - Arguments to log
*/
function log(level, ...args) {
const icons = {
debug: chalk.gray("🔍"),
info: chalk.blue("ℹ️"),
warn: chalk.yellow("⚠️"),
error: chalk.red("❌"),
success: chalk.green("✅"),
};
if (LOG_LEVELS[level] >= LOG_LEVEL) {
const icon = icons[level] || "";
if (level === "error") {
console.error(icon, chalk.red(...args));
} else if (level === "warn") {
console.warn(icon, chalk.yellow(...args));
} else if (level === "success") {
console.log(icon, chalk.green(...args));
} else if (level === "info") {
console.log(icon, chalk.blue(...args));
} else {
console.log(icon, ...args);
}
}
}
/**
* Create a logger object with methods for different log levels
* Can be used as a drop-in replacement for existing logger initialization
* @returns {Object} Logger object with info, error, debug, warn, and success methods
*/
export function createLogger() {
return {
debug: (message) => log("debug", message),
info: (message) => log("info", message),
warn: (message) => log("warn", message),
error: (message) => log("error", message),
success: (message) => log("success", message),
log: log, // Also expose the raw log function
};
}
// Export a default logger instance
const logger = createLogger();
export default logger;
export { log, LOG_LEVELS };

66
mcp-server/src/tools/addTask.js Normal file
View File

@@ -0,0 +1,66 @@
/**
* tools/addTask.js
* Tool to add a new task using AI
*/
import { z } from "zod";
import {
executeTaskMasterCommand,
createContentResponse,
createErrorResponse,
} from "./utils.js";
/**
* Register the addTask tool with the MCP server
* @param {FastMCP} server - FastMCP server instance
*/
export function registerAddTaskTool(server) {
server.addTool({
name: "addTask",
description: "Add a new task using AI",
parameters: z.object({
prompt: z.string().describe("Description of the task to add"),
dependencies: z
.string()
.optional()
.describe("Comma-separated list of task IDs this task depends on"),
priority: z
.string()
.optional()
.describe("Task priority (high, medium, low)"),
file: z.string().optional().describe("Path to the tasks file"),
projectRoot: z
.string()
.describe(
"Root directory of the project (default: current working directory)"
),
}),
execute: async (args, { log }) => {
try {
log.info(`Adding new task: ${args.prompt}`);
const cmdArgs = [`--prompt="${args.prompt}"`];
if (args.dependencies)
cmdArgs.push(`--dependencies=${args.dependencies}`);
if (args.priority) cmdArgs.push(`--priority=${args.priority}`);
if (args.file) cmdArgs.push(`--file=${args.file}`);
const result = executeTaskMasterCommand(
"add-task",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);
}
return createContentResponse(result.stdout);
} catch (error) {
log.error(`Error adding task: ${error.message}`);
return createErrorResponse(`Error adding task: ${error.message}`);
}
},
});
}

78
mcp-server/src/tools/expandTask.js Normal file
View File

@@ -0,0 +1,78 @@
/**
* tools/expandTask.js
* Tool to break down a task into detailed subtasks
*/
import { z } from "zod";
import {
executeTaskMasterCommand,
createContentResponse,
createErrorResponse,
} from "./utils.js";
/**
* Register the expandTask tool with the MCP server
* @param {Object} server - FastMCP server instance
*/
export function registerExpandTaskTool(server) {
server.addTool({
name: "expandTask",
description: "Break down a task into detailed subtasks",
parameters: z.object({
id: z.string().describe("Task ID to expand"),
num: z.number().optional().describe("Number of subtasks to generate"),
research: z
.boolean()
.optional()
.describe(
"Enable Perplexity AI for research-backed subtask generation"
),
prompt: z
.string()
.optional()
.describe("Additional context to guide subtask generation"),
force: z
.boolean()
.optional()
.describe(
"Force regeneration of subtasks for tasks that already have them"
),
file: z.string().optional().describe("Path to the tasks file"),
projectRoot: z
.string()
.describe(
"Root directory of the project (default: current working directory)"
),
}),
execute: async (args, { log }) => {
try {
log.info(`Expanding task ${args.id}`);
const cmdArgs = [`--id=${args.id}`];
if (args.num) cmdArgs.push(`--num=${args.num}`);
if (args.research) cmdArgs.push("--research");
if (args.prompt) cmdArgs.push(`--prompt="${args.prompt}"`);
if (args.force) cmdArgs.push("--force");
if (args.file) cmdArgs.push(`--file=${args.file}`);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"expand",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);
}
return createContentResponse(result.stdout);
} catch (error) {
log.error(`Error expanding task: ${error.message}`);
return createErrorResponse(`Error expanding task: ${error.message}`);
}
},
});
}

29
mcp-server/src/tools/index.js Normal file
View File

@@ -0,0 +1,29 @@
/**
* tools/index.js
* Export all Task Master CLI tools for MCP server
*/
import logger from "../logger.js";
import { registerListTasksTool } from "./listTasks.js";
import { registerShowTaskTool } from "./showTask.js";
import { registerSetTaskStatusTool } from "./setTaskStatus.js";
import { registerExpandTaskTool } from "./expandTask.js";
import { registerNextTaskTool } from "./nextTask.js";
import { registerAddTaskTool } from "./addTask.js";
/**
* Register all Task Master tools with the MCP server
* @param {Object} server - FastMCP server instance
*/
export function registerTaskMasterTools(server) {
registerListTasksTool(server);
registerShowTaskTool(server);
registerSetTaskStatusTool(server);
registerExpandTaskTool(server);
registerNextTaskTool(server);
registerAddTaskTool(server);
}
export default {
registerTaskMasterTools,
};

65
mcp-server/src/tools/listTasks.js Normal file
View File

@@ -0,0 +1,65 @@
/**
* tools/listTasks.js
* Tool to list all tasks from Task Master
*/
import { z } from "zod";
import {
executeTaskMasterCommand,
createContentResponse,
createErrorResponse,
} from "./utils.js";
/**
* Register the listTasks tool with the MCP server
* @param {Object} server - FastMCP server instance
*/
export function registerListTasksTool(server) {
server.addTool({
name: "listTasks",
description: "List all tasks from Task Master",
parameters: z.object({
status: z.string().optional().describe("Filter tasks by status"),
withSubtasks: z
.boolean()
.optional()
.describe("Include subtasks in the response"),
file: z.string().optional().describe("Path to the tasks file"),
projectRoot: z
.string()
.describe(
"Root directory of the project (default: current working directory)"
),
}),
execute: async (args, { log }) => {
try {
log.info(`Listing tasks with filters: ${JSON.stringify(args)}`);
const cmdArgs = [];
if (args.status) cmdArgs.push(`--status=${args.status}`);
if (args.withSubtasks) cmdArgs.push("--with-subtasks");
if (args.file) cmdArgs.push(`--file=${args.file}`);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"list",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);
}
log.info(`Listing tasks result: ${result.stdout}`, result.stdout);
return createContentResponse(result.stdout);
} catch (error) {
log.error(`Error listing tasks: ${error.message}`);
return createErrorResponse(`Error listing tasks: ${error.message}`);
}
},
});
}

57
mcp-server/src/tools/nextTask.js Normal file
View File

@@ -0,0 +1,57 @@
/**
* tools/nextTask.js
* Tool to show the next task to work on based on dependencies and status
*/
import { z } from "zod";
import {
executeTaskMasterCommand,
createContentResponse,
createErrorResponse,
} from "./utils.js";
/**
* Register the nextTask tool with the MCP server
* @param {Object} server - FastMCP server instance
*/
export function registerNextTaskTool(server) {
server.addTool({
name: "nextTask",
description:
"Show the next task to work on based on dependencies and status",
parameters: z.object({
file: z.string().optional().describe("Path to the tasks file"),
projectRoot: z
.string()
.describe(
"Root directory of the project (default: current working directory)"
),
}),
execute: async (args, { log }) => {
try {
log.info(`Finding next task to work on`);
const cmdArgs = [];
if (args.file) cmdArgs.push(`--file=${args.file}`);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"next",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);
}
return createContentResponse(result.stdout);
} catch (error) {
log.error(`Error finding next task: ${error.message}`);
return createErrorResponse(`Error finding next task: ${error.message}`);
}
},
});
}

64
mcp-server/src/tools/setTaskStatus.js Normal file
View File

@@ -0,0 +1,64 @@
/**
* tools/setTaskStatus.js
* Tool to set the status of a task
*/
import { z } from "zod";
import {
executeTaskMasterCommand,
createContentResponse,
createErrorResponse,
} from "./utils.js";
/**
* Register the setTaskStatus tool with the MCP server
* @param {Object} server - FastMCP server instance
*/
export function registerSetTaskStatusTool(server) {
server.addTool({
name: "setTaskStatus",
description: "Set the status of a task",
parameters: z.object({
id: z
.string()
.describe("Task ID (can be comma-separated for multiple tasks)"),
status: z
.string()
.describe("New status (todo, in-progress, review, done)"),
file: z.string().optional().describe("Path to the tasks file"),
projectRoot: z
.string()
.describe(
"Root directory of the project (default: current working directory)"
),
}),
execute: async (args, { log }) => {
try {
log.info(`Setting status of task(s) ${args.id} to: ${args.status}`);
const cmdArgs = [`--id=${args.id}`, `--status=${args.status}`];
if (args.file) cmdArgs.push(`--file=${args.file}`);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"set-status",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);
}
return createContentResponse(result.stdout);
} catch (error) {
log.error(`Error setting task status: ${error.message}`);
return createErrorResponse(
`Error setting task status: ${error.message}`
);
}
},
});
}

57
mcp-server/src/tools/showTask.js Normal file
View File

@@ -0,0 +1,57 @@
/**
* tools/showTask.js
* Tool to show detailed information about a specific task
*/
import { z } from "zod";
import {
executeTaskMasterCommand,
createContentResponse,
createErrorResponse,
} from "./utils.js";
/**
* Register the showTask tool with the MCP server
* @param {Object} server - FastMCP server instance
*/
export function registerShowTaskTool(server) {
server.addTool({
name: "showTask",
description: "Show detailed information about a specific task",
parameters: z.object({
id: z.string().describe("Task ID to show"),
file: z.string().optional().describe("Path to the tasks file"),
projectRoot: z
.string()
.describe(
"Root directory of the project (default: current working directory)"
),
}),
execute: async (args, { log }) => {
try {
log.info(`Showing task details for ID: ${args.id}`);
const cmdArgs = [`--id=${args.id}`];
if (args.file) cmdArgs.push(`--file=${args.file}`);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"show",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);
}
return createContentResponse(result.stdout);
} catch (error) {
log.error(`Error showing task: ${error.message}`);
return createErrorResponse(`Error showing task: ${error.message}`);
}
},
});
}

108
mcp-server/src/tools/utils.js Normal file
View File

@@ -0,0 +1,108 @@
/**
* tools/utils.js
* Utility functions for Task Master CLI integration
*/
import { spawnSync } from "child_process";
/**
* Execute a Task Master CLI command using child_process
* @param {string} command - The command to execute
* @param {Object} log - The logger object from FastMCP
* @param {Array} args - Arguments for the command
* @param {string} cwd - Working directory for command execution (defaults to current project root)
* @returns {Object} - The result of the command execution
*/
export function executeTaskMasterCommand(
command,
log,
args = [],
cwd = process.cwd()
) {
try {
log.info(
`Executing task-master ${command} with args: ${JSON.stringify(
args
)} in directory: ${cwd}`
);
// Prepare full arguments array
const fullArgs = [command, ...args];
// Common options for spawn
const spawnOptions = {
encoding: "utf8",
cwd: cwd,
};
// Execute the command using the global task-master CLI or local script
// Try the global CLI first
let result = spawnSync("task-master", fullArgs, spawnOptions);
// If global CLI is not available, try fallback to the local script
if (result.error && result.error.code === "ENOENT") {
log.info("Global task-master not found, falling back to local script");
result = spawnSync("node", ["scripts/dev.js", ...fullArgs], spawnOptions);
}
if (result.error) {
throw new Error(`Command execution error: ${result.error.message}`);
}
if (result.status !== 0) {
// Improve error handling by combining stderr and stdout if stderr is empty
const errorOutput = result.stderr
? result.stderr.trim()
: result.stdout
? result.stdout.trim()
: "Unknown error";
throw new Error(
`Command failed with exit code ${result.status}: ${errorOutput}`
);
}
return {
success: true,
stdout: result.stdout,
stderr: result.stderr,
};
} catch (error) {
log.error(`Error executing task-master command: ${error.message}`);
return {
success: false,
error: error.message,
};
}
}
/**
* Creates standard content response for tools
* @param {string} text - Text content to include in response
* @returns {Object} - Content response object
*/
export function createContentResponse(text) {
return {
content: [
{
text,
type: "text",
},
],
};
}
/**
* Creates error response for tools
* @param {string} errorMessage - Error message to include in response
* @returns {Object} - Error content response object
*/
export function createErrorResponse(errorMessage) {
return {
content: [
{
text: errorMessage,
type: "text",
},
],
};
}

2590
package-lock.json generated
View File

File diff suppressed because it is too large Load Diff

24
package.json
View File

@@ -6,7 +6,8 @@
"type": "module",
"bin": {
"task-master": "bin/task-master.js",
"task-master-init": "bin/task-master-init.js"
"task-master-init": "bin/task-master-init.js",
"task-master-mcp-server": "mcp-server/server.js"
},
"scripts": {
"test": "node --experimental-vm-modules node_modules/.bin/jest",
@@ -14,7 +15,9 @@
"test:coverage": "node --experimental-vm-modules node_modules/.bin/jest --coverage",
"prepare-package": "node scripts/prepare-package.js",
"prepublishOnly": "npm run prepare-package",
"prepare": "chmod +x bin/task-master.js bin/task-master-init.js"
"prepare": "chmod +x bin/task-master.js bin/task-master-init.js",
"changeset": "changeset",
"release": "changeset publish"
},
"keywords": [
"claude",
@@ -24,7 +27,9 @@
"development",
"cursor",
"anthropic",
"llm"
"llm",
"mcp",
"context"
],
"author": "Eyal Toledano",
"license": "MIT",
@@ -34,11 +39,17 @@
"chalk": "^4.1.2",
"cli-table3": "^0.6.5",
"commander": "^11.1.0",
"cors": "^2.8.5",
"dotenv": "^16.3.1",
"express": "^4.21.2",
"fastmcp": "^1.20.5",
"figlet": "^1.8.0",
"gradient-string": "^3.0.0",
"helmet": "^8.1.0",
"jsonwebtoken": "^9.0.2",
"openai": "^4.89.0",
"ora": "^8.2.0"
"ora": "^8.2.0",
"fuse.js": "^7.0.0"
},
"engines": {
"node": ">=14.0.0"
@@ -59,13 +70,16 @@
".cursor/**",
"README-task-master.md",
"index.js",
"bin/**"
"bin/**",
"mcp-server/**"
],
"overrides": {
"node-fetch": "^3.3.2",
"whatwg-url": "^11.0.0"
},
"devDependencies": {
"@changesets/changelog-github": "^0.5.1",
"@changesets/cli": "^2.28.1",
"@types/jest": "^29.5.14",
"jest": "^29.7.0",
"jest-environment-node": "^29.7.0",

115
tasks/task_023.txt
View File

@@ -56,3 +56,118 @@ Testing for the MCP server functionality should include:
- Test for common API vulnerabilities (injection, CSRF, etc.)
All tests should be automated and included in the CI/CD pipeline. Documentation should include examples of how to test the MCP server functionality manually using tools like curl or Postman.
# Subtasks:
## 1. Create Core MCP Server Module and Basic Structure [done]
### Dependencies: None
### Description: Create the foundation for the MCP server implementation by setting up the core module structure, configuration, and server initialization.
### Details:
Implementation steps:
1. Create a new module `mcp-server.js` with the basic server structure
2. Implement configuration options to enable/disable the MCP server
3. Set up Express.js routes for the required MCP endpoints (/context, /models, /execute)
4. Create middleware for request validation and response formatting
5. Implement basic error handling according to MCP specifications
6. Add logging infrastructure for MCP operations
7. Create initialization and shutdown procedures for the MCP server
8. Set up integration with the main Task Master application
Testing approach:
- Unit tests for configuration loading and validation
- Test server initialization and shutdown procedures
- Verify that routes are properly registered
- Test basic error handling with invalid requests
## 2. Implement Context Management System [done]
### Dependencies: 23.1
### Description: Develop a robust context management system that can efficiently store, retrieve, and manipulate context data according to the MCP specification.
### Details:
Implementation steps:
1. Design and implement data structures for context storage
2. Create methods for context creation, retrieval, updating, and deletion
3. Implement context windowing and truncation algorithms for handling size limits
4. Add support for context metadata and tagging
5. Create utilities for context serialization and deserialization
6. Implement efficient indexing for quick context lookups
7. Add support for context versioning and history
8. Develop mechanisms for context persistence (in-memory, disk-based, or database)
Testing approach:
- Unit tests for all context operations (CRUD)
- Performance tests for context retrieval with various sizes
- Test context windowing and truncation with edge cases
- Verify metadata handling and tagging functionality
- Test persistence mechanisms with simulated failures
## 3. Implement MCP Endpoints and API Handlers [done]
### Dependencies: 23.1, 23.2
### Description: Develop the complete API handlers for all required MCP endpoints, ensuring they follow the protocol specification and integrate with the context management system.
### Details:
Implementation steps:
1. Implement the `/context` endpoint for:
- GET: retrieving existing context
- POST: creating new context
- PUT: updating existing context
- DELETE: removing context
2. Implement the `/models` endpoint to list available models
3. Develop the `/execute` endpoint for performing operations with context
4. Create request validators for each endpoint
5. Implement response formatters according to MCP specifications
6. Add detailed error handling for each endpoint
7. Set up proper HTTP status codes for different scenarios
8. Implement pagination for endpoints that return lists
Testing approach:
- Unit tests for each endpoint handler
- Integration tests with mock context data
- Test various request formats and edge cases
- Verify response formats match MCP specifications
- Test error handling with invalid inputs
- Benchmark endpoint performance
## 4. Implement Authentication and Authorization System [pending]
### Dependencies: 23.1, 23.3
### Description: Create a secure authentication and authorization mechanism for MCP clients to ensure only authorized applications can access the MCP server functionality.
### Details:
Implementation steps:
1. Design authentication scheme (API keys, OAuth, JWT, etc.)
2. Implement authentication middleware for all MCP endpoints
3. Create an API key management system for client applications
4. Develop role-based access control for different operations
5. Implement rate limiting to prevent abuse
6. Add secure token validation and handling
7. Create endpoints for managing client credentials
8. Implement audit logging for authentication events
Testing approach:
- Security testing for authentication mechanisms
- Test access control with various permission levels
- Verify rate limiting functionality
- Test token validation with valid and invalid tokens
- Simulate unauthorized access attempts
- Verify audit logs contain appropriate information
## 5. Optimize Performance and Finalize Documentation [pending]
### Dependencies: 23.1, 23.2, 23.3, 23.4
### Description: Optimize the MCP server implementation for performance, especially for context retrieval operations, and create comprehensive documentation for users.
### Details:
Implementation steps:
1. Profile the MCP server to identify performance bottlenecks
2. Implement caching mechanisms for frequently accessed contexts
3. Optimize context serialization and deserialization
4. Add connection pooling for database operations (if applicable)
5. Implement request batching for bulk operations
6. Create comprehensive API documentation with examples
7. Add setup and configuration guides to the Task Master documentation
8. Create example client implementations
9. Add monitoring endpoints for server health and metrics
10. Implement graceful degradation under high load
Testing approach:
- Load testing with simulated concurrent clients
- Measure response times for various operations
- Test with large context sizes to verify performance
- Verify documentation accuracy with sample requests
- Test monitoring endpoints
- Perform stress testing to identify failure points

64
tasks/tasks.json
View File

@@ -1343,8 +1343,68 @@
22
],
"priority": "medium",
"details": "This task involves implementing the Model Context Protocol server capabilities within Task Master using FastMCP. The implementation should:\n\n1. Use FastMCP to create the MCP server module (`mcp-server.ts` or equivalent)\n2. Implement the required MCP endpoints using FastMCP:\n - `/context` - For retrieving and updating context\n - `/models` - For listing available models\n - `/execute` - For executing operations with context\n3. Utilize FastMCP's built-in features for context management, including:\n - Efficient context storage and retrieval\n - Context windowing and truncation\n - Metadata and tagging support\n4. Add authentication and authorization mechanisms using FastMCP capabilities\n5. Implement error handling and response formatting as per MCP specifications\n6. Configure Task Master to enable/disable MCP server functionality via FastMCP settings\n7. Add documentation on using Task Master as an MCP server with FastMCP\n8. Ensure compatibility with existing MCP clients by adhering to FastMCP's compliance features\n9. Optimize performance using FastMCP tools, especially for context retrieval operations\n10. Add logging for MCP server operations using FastMCP's logging utilities\n\nThe implementation should follow RESTful API design principles and leverage FastMCP's concurrency handling for multiple client requests. Consider using TypeScript for better type safety and integration with FastMCP[1][2].",
"testStrategy": "Testing for the MCP server functionality should include:\n\n1. Unit tests:\n - Test each MCP endpoint handler function independently using FastMCP\n - Verify context storage and retrieval mechanisms provided by FastMCP\n - Test authentication and authorization logic\n - Validate error handling for various failure scenarios\n\n2. Integration tests:\n - Set up a test MCP server instance using FastMCP\n - Test complete request/response cycles for each endpoint\n - Verify context persistence across multiple requests\n - Test with various payload sizes and content types\n\n3. Compatibility tests:\n - Test with existing MCP client libraries\n - Verify compliance with the MCP specification\n - Ensure backward compatibility with any MCP versions supported by FastMCP\n\n4. Performance tests:\n - Measure response times for context operations with various context sizes\n - Test concurrent request handling using FastMCP's concurrency tools\n - Verify memory usage remains within acceptable limits during extended operation\n\n5. Security tests:\n - Verify authentication mechanisms cannot be bypassed\n - Test for common API vulnerabilities (injection, CSRF, etc.)\n\nAll tests should be automated and included in the CI/CD pipeline. Documentation should include examples of how to test the MCP server functionality manually using tools like curl or Postman."
"details": "This task involves implementing the Model Context Protocol server capabilities within Task Master. The implementation should:\n\n1. Create a new module `mcp-server.js` that implements the core MCP server functionality\n2. Implement the required MCP endpoints:\n - `/context` - For retrieving and updating context\n - `/models` - For listing available models\n - `/execute` - For executing operations with context\n3. Develop a context management system that can:\n - Store and retrieve context data efficiently\n - Handle context windowing and truncation when limits are reached\n - Support context metadata and tagging\n4. Add authentication and authorization mechanisms for MCP clients\n5. Implement proper error handling and response formatting according to MCP specifications\n6. Create configuration options in Task Master to enable/disable the MCP server functionality\n7. Add documentation for how to use Task Master as an MCP server\n8. Ensure the implementation is compatible with existing MCP clients\n9. Optimize for performance, especially for context retrieval operations\n10. Add logging for MCP server operations\n\nThe implementation should follow RESTful API design principles and should be able to handle concurrent requests from multiple clients.",
"testStrategy": "Testing for the MCP server functionality should include:\n\n1. Unit tests:\n - Test each MCP endpoint handler function independently\n - Verify context storage and retrieval mechanisms\n - Test authentication and authorization logic\n - Validate error handling for various failure scenarios\n\n2. Integration tests:\n - Set up a test MCP server instance\n - Test complete request/response cycles for each endpoint\n - Verify context persistence across multiple requests\n - Test with various payload sizes and content types\n\n3. Compatibility tests:\n - Test with existing MCP client libraries\n - Verify compliance with the MCP specification\n - Ensure backward compatibility with any MCP versions supported\n\n4. Performance tests:\n - Measure response times for context operations with various context sizes\n - Test concurrent request handling\n - Verify memory usage remains within acceptable limits during extended operation\n\n5. Security tests:\n - Verify authentication mechanisms cannot be bypassed\n - Test for common API vulnerabilities (injection, CSRF, etc.)\n\nAll tests should be automated and included in the CI/CD pipeline. Documentation should include examples of how to test the MCP server functionality manually using tools like curl or Postman.",
"subtasks": [
{
"id": 1,
"title": "Create Core MCP Server Module and Basic Structure",
"description": "Create the foundation for the MCP server implementation by setting up the core module structure, configuration, and server initialization.",
"dependencies": [],
"details": "Implementation steps:\n1. Create a new module `mcp-server.js` with the basic server structure\n2. Implement configuration options to enable/disable the MCP server\n3. Set up Express.js routes for the required MCP endpoints (/context, /models, /execute)\n4. Create middleware for request validation and response formatting\n5. Implement basic error handling according to MCP specifications\n6. Add logging infrastructure for MCP operations\n7. Create initialization and shutdown procedures for the MCP server\n8. Set up integration with the main Task Master application\n\nTesting approach:\n- Unit tests for configuration loading and validation\n- Test server initialization and shutdown procedures\n- Verify that routes are properly registered\n- Test basic error handling with invalid requests",
"status": "done",
"parentTaskId": 23
},
{
"id": 2,
"title": "Implement Context Management System",
"description": "Develop a robust context management system that can efficiently store, retrieve, and manipulate context data according to the MCP specification.",
"dependencies": [
1
],
"details": "Implementation steps:\n1. Design and implement data structures for context storage\n2. Create methods for context creation, retrieval, updating, and deletion\n3. Implement context windowing and truncation algorithms for handling size limits\n4. Add support for context metadata and tagging\n5. Create utilities for context serialization and deserialization\n6. Implement efficient indexing for quick context lookups\n7. Add support for context versioning and history\n8. Develop mechanisms for context persistence (in-memory, disk-based, or database)\n\nTesting approach:\n- Unit tests for all context operations (CRUD)\n- Performance tests for context retrieval with various sizes\n- Test context windowing and truncation with edge cases\n- Verify metadata handling and tagging functionality\n- Test persistence mechanisms with simulated failures",
"status": "done",
"parentTaskId": 23
},
{
"id": 3,
"title": "Implement MCP Endpoints and API Handlers",
"description": "Develop the complete API handlers for all required MCP endpoints, ensuring they follow the protocol specification and integrate with the context management system.",
"dependencies": [
1,
2
],
"details": "Implementation steps:\n1. Implement the `/context` endpoint for:\n - GET: retrieving existing context\n - POST: creating new context\n - PUT: updating existing context\n - DELETE: removing context\n2. Implement the `/models` endpoint to list available models\n3. Develop the `/execute` endpoint for performing operations with context\n4. Create request validators for each endpoint\n5. Implement response formatters according to MCP specifications\n6. Add detailed error handling for each endpoint\n7. Set up proper HTTP status codes for different scenarios\n8. Implement pagination for endpoints that return lists\n\nTesting approach:\n- Unit tests for each endpoint handler\n- Integration tests with mock context data\n- Test various request formats and edge cases\n- Verify response formats match MCP specifications\n- Test error handling with invalid inputs\n- Benchmark endpoint performance",
"status": "done",
"parentTaskId": 23
},
{
"id": 4,
"title": "Implement Authentication and Authorization System",
"description": "Create a secure authentication and authorization mechanism for MCP clients to ensure only authorized applications can access the MCP server functionality.",
"dependencies": [
1,
3
],
"details": "Implementation steps:\n1. Design authentication scheme (API keys, OAuth, JWT, etc.)\n2. Implement authentication middleware for all MCP endpoints\n3. Create an API key management system for client applications\n4. Develop role-based access control for different operations\n5. Implement rate limiting to prevent abuse\n6. Add secure token validation and handling\n7. Create endpoints for managing client credentials\n8. Implement audit logging for authentication events\n\nTesting approach:\n- Security testing for authentication mechanisms\n- Test access control with various permission levels\n- Verify rate limiting functionality\n- Test token validation with valid and invalid tokens\n- Simulate unauthorized access attempts\n- Verify audit logs contain appropriate information",
"status": "pending",
"parentTaskId": 23
},
{
"id": 5,
"title": "Optimize Performance and Finalize Documentation",
"description": "Optimize the MCP server implementation for performance, especially for context retrieval operations, and create comprehensive documentation for users.",
"dependencies": [
1,
2,
3,
4
],
"details": "Implementation steps:\n1. Profile the MCP server to identify performance bottlenecks\n2. Implement caching mechanisms for frequently accessed contexts\n3. Optimize context serialization and deserialization\n4. Add connection pooling for database operations (if applicable)\n5. Implement request batching for bulk operations\n6. Create comprehensive API documentation with examples\n7. Add setup and configuration guides to the Task Master documentation\n8. Create example client implementations\n9. Add monitoring endpoints for server health and metrics\n10. Implement graceful degradation under high load\n\nTesting approach:\n- Load testing with simulated concurrent clients\n- Measure response times for various operations\n- Test with large context sizes to verify performance\n- Verify documentation accuracy with sample requests\n- Test monitoring endpoints\n- Perform stress testing to identify failure points",
"status": "pending",
"parentTaskId": 23
}
]
},
{
"id": 24,