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

fix(mcp): get everything working, cleanup, and test all tools

Browse Source
This commit is contained in:
Ralph Khreish
2025-03-25 19:00:00 +00:00
parent 37c5b83f60
commit 3582798293
11 changed files with 241 additions and 201 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.cursor/mcp.json
View File

@@ -1,8 +0,0 @@
{
"mcpServers": {
"taskMaster": {
"command": "node",
"args": ["mcp-server/server.js"]
}
}
}

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 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?
```

64
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 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"
@@ -866,6 +915,7 @@ 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 +923,7 @@ 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 +932,7 @@ 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 +945,14 @@ 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 +969,7 @@ 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 +984,7 @@ 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 +1015,51 @@ 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?
```

170
mcp-server/README.md
View File

@@ -1,170 +0,0 @@
# Task Master MCP Server
This module implements a [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for Task Master, allowing external applications to access Task Master functionality and context through a standardized API.
## Features
- MCP-compliant server implementation using FastMCP
- RESTful API for context management
- Authentication and authorization for secure access
- Context storage and retrieval with metadata and tagging
- Context windowing and truncation for handling size limits
- Integration with Task Master for task management operations
## Installation
The MCP server is included with Task Master. Install Task Master globally to use the MCP server:
```bash
npm install -g task-master-ai
```
Or use it locally:
```bash
npm install task-master-ai
```
## Environment Configuration
The MCP server can be configured using environment variables or a `.env` file:
| Variable | Description | Default |
| -------------------- | ---------------------------------------- | ----------------------------- |
| `MCP_SERVER_PORT` | Port for the MCP server | 3000 |
| `MCP_SERVER_HOST` | Host for the MCP server | localhost |
| `MCP_CONTEXT_DIR` | Directory for context storage | ./mcp-server/contexts |
| `MCP_API_KEYS_FILE` | File for API key storage | ./mcp-server/api-keys.json |
| `MCP_JWT_SECRET` | Secret for JWT token generation | task-master-mcp-server-secret |
| `MCP_JWT_EXPIRATION` | JWT token expiration time | 24h |
| `LOG_LEVEL` | Logging level (debug, info, warn, error) | info |
## Getting Started
### Starting the Server
Start the MCP server as a standalone process:
```bash
npx task-master-mcp-server
```
Or start it programmatically:
```javascript
import { TaskMasterMCPServer } from "task-master-ai/mcp-server";
const server = new TaskMasterMCPServer();
await server.start({ port: 3000, host: "localhost" });
```
### Authentication
The MCP server uses API key authentication with JWT tokens for secure access. A default admin API key is generated on first startup and can be found in the `api-keys.json` file.
To get a JWT token:
```bash
curl -X POST http://localhost:3000/auth/token \
-H "x-api-key: YOUR_API_KEY"
```
Use the token for subsequent requests:
```bash
curl http://localhost:3000/mcp/tools \
-H "Authorization: Bearer YOUR_JWT_TOKEN"
```
### Creating a New API Key
Admin users can create new API keys:
```bash
curl -X POST http://localhost:3000/auth/api-keys \
-H "Authorization: Bearer ADMIN_JWT_TOKEN" \
-H "Content-Type: application/json" \
-d '{"clientId": "user1", "role": "user"}'
```
## Available MCP Endpoints
The MCP server implements the following MCP-compliant endpoints:
### Context Management
- `GET /mcp/context` - List all contexts
- `POST /mcp/context` - Create a new context
- `GET /mcp/context/{id}` - Get a specific context
- `PUT /mcp/context/{id}` - Update a context
- `DELETE /mcp/context/{id}` - Delete a context
### Models
- `GET /mcp/models` - List available models
- `GET /mcp/models/{id}` - Get model details
### Execution
- `POST /mcp/execute` - Execute an operation with context
## Available MCP Tools
The MCP server provides the following tools:
### Context Tools
- `createContext` - Create a new context
- `getContext` - Retrieve a context by ID
- `updateContext` - Update an existing context
- `deleteContext` - Delete a context
- `listContexts` - List available contexts
- `addTags` - Add tags to a context
- `truncateContext` - Truncate a context to a maximum size
### Task Master Tools
- `listTasks` - List tasks from Task Master
- `getTaskDetails` - Get detailed task information
- `executeWithContext` - Execute operations using context
## Examples
### Creating a Context
```javascript
// Using the MCP client
const client = new MCPClient("http://localhost:3000");
await client.authenticate("YOUR_API_KEY");
const context = await client.createContext("my-context", {
title: "My Project",
tasks: ["Implement feature X", "Fix bug Y"],
});
```
### Executing an Operation with Context
```javascript
// Using the MCP client
const result = await client.execute("generateTask", "my-context", {
title: "New Task",
description: "Create a new task based on context",
});
```
## Integration with Other Tools
The Task Master MCP server can be integrated with other MCP-compatible tools and clients:
- LLM applications that support the MCP protocol
- Task management systems that support context-aware operations
- Development environments with MCP integration
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## License
This project is licensed under the MIT License - see the LICENSE file for details.

12
mcp-server/src/tools/addTask.js
View File

@@ -29,6 +29,11 @@ export function registerAddTaskTool(server) {
.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 {
@@ -40,7 +45,12 @@ export function registerAddTaskTool(server) {
if (args.priority) cmdArgs.push(`--priority=${args.priority}`);
if (args.file) cmdArgs.push(`--file=${args.file}`);
const result = executeTaskMasterCommand("add-task", log, cmdArgs);
const result = executeTaskMasterCommand(
"add-task",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);

16
mcp-server/src/tools/expandTask.js
View File

@@ -19,7 +19,7 @@ export function registerExpandTaskTool(server) {
name: "expandTask",
description: "Break down a task into detailed subtasks",
parameters: z.object({
id: z.union([z.string(), z.number()]).describe("Task ID to expand"),
id: z.string().describe("Task ID to expand"),
num: z.number().optional().describe("Number of subtasks to generate"),
research: z
.boolean()
@@ -38,6 +38,11 @@ export function registerExpandTaskTool(server) {
"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 {
@@ -50,7 +55,14 @@ export function registerExpandTaskTool(server) {
if (args.force) cmdArgs.push("--force");
if (args.file) cmdArgs.push(`--file=${args.file}`);
const result = executeTaskMasterCommand("expand", log, cmdArgs);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"expand",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);

16
mcp-server/src/tools/listTasks.js
View File

@@ -25,6 +25,11 @@ export function registerListTasksTool(server) {
.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 {
@@ -35,12 +40,21 @@ export function registerListTasksTool(server) {
if (args.withSubtasks) cmdArgs.push("--with-subtasks");
if (args.file) cmdArgs.push(`--file=${args.file}`);
const result = executeTaskMasterCommand("list", log, cmdArgs);
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}`);

14
mcp-server/src/tools/nextTask.js
View File

@@ -21,6 +21,11 @@ export function registerNextTaskTool(server) {
"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 {
@@ -29,7 +34,14 @@ export function registerNextTaskTool(server) {
const cmdArgs = [];
if (args.file) cmdArgs.push(`--file=${args.file}`);
const result = executeTaskMasterCommand("next", log, cmdArgs);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"next",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);

16
mcp-server/src/tools/setTaskStatus.js
View File

@@ -20,12 +20,17 @@ export function registerSetTaskStatusTool(server) {
description: "Set the status of a task",
parameters: z.object({
id: z
.union([z.string(), z.number()])
.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 {
@@ -34,7 +39,14 @@ export function registerSetTaskStatusTool(server) {
const cmdArgs = [`--id=${args.id}`, `--status=${args.status}`];
if (args.file) cmdArgs.push(`--file=${args.file}`);
const result = executeTaskMasterCommand("set-status", log, cmdArgs);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"set-status",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);

18
mcp-server/src/tools/showTask.js
View File

@@ -19,17 +19,29 @@ export function registerShowTaskTool(server) {
name: "showTask",
description: "Show detailed information about a specific task",
parameters: z.object({
id: z.union([z.string(), z.number()]).describe("Task ID to show"),
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: ${args.id}`);
const cmdArgs = [args.id];
const cmdArgs = [`--id=${args.id}`];
if (args.file) cmdArgs.push(`--file=${args.file}`);
const result = executeTaskMasterCommand("show", log, cmdArgs);
const projectRoot = args.projectRoot;
const result = executeTaskMasterCommand(
"show",
log,
cmdArgs,
projectRoot
);
if (!result.success) {
throw new Error(result.error);

32
mcp-server/src/tools/utils.js
View File

@@ -10,27 +10,39 @@ import { spawnSync } from "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 = []) {
export function executeTaskMasterCommand(
command,
log,
args = [],
cwd = process.cwd()
) {
try {
log.info(
`Executing task-master ${command} with args: ${JSON.stringify(args)}`
`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, { encoding: "utf8" });
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], {
encoding: "utf8",
});
result = spawnSync("node", ["scripts/dev.js", ...fullArgs], spawnOptions);
}
if (result.error) {
@@ -38,8 +50,14 @@ export function executeTaskMasterCommand(command, log, args = []) {
}
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}: ${result.stderr}`
`Command failed with exit code ${result.status}: ${errorOutput}`
);
}