feat: Tool Consolidation - Reduce MCP Tools by 38% (v2.26.0) (#439)

* feat: Remove 9 low-value tools and consolidate n8n_health_check (v2.25.0)

Telemetry-driven tool cleanup to improve API clarity:

**Removed Tools (9):**
- list_nodes - Use search_nodes instead
- list_ai_tools - Use search_nodes with isAITool filter
- list_tasks - Low usage (0.02%)
- get_database_statistics - Use n8n_health_check
- list_templates - Use search_templates or get_templates_for_task
- get_node_as_tool_info - Documented in get_node
- validate_workflow_connections - Use validate_workflow
- validate_workflow_expressions - Use validate_workflow
- n8n_list_available_tools - Use n8n_health_check
- n8n_diagnostic - Merged into n8n_health_check

**Consolidated Tool:**
- n8n_health_check now supports mode='diagnostic' for detailed troubleshooting

**Tool Count:**
- Before: 38 tools
- After: 31 tools (18% reduction)

Concieved by Romuald Członkowski - www.aiadvisors.pl/en

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: cleanup stale references and update tests after tool removal

- Remove handleListAvailableTools dead code from handlers-n8n-manager.ts
- Update error messages to reference n8n_health_check(mode="diagnostic") instead of n8n_diagnostic
- Update tool counts in diagnostic messages (14 doc tools, 31 total)
- Fix error-handling.test.ts to use valid tools (search_nodes, tools_documentation)
- Remove obsolete list-tools.test.ts integration tests
- Remove unused ListToolsResponse type from response-types.ts
- Update tools.ts QUICK REFERENCE to remove list_nodes references
- Update tools-documentation.ts to remove references to removed tools
- Update tool-docs files to remove stale relatedTools references
- Fix tools.test.ts to not test removed tools (list_nodes, list_ai_tools, etc.)
- Fix parameter-validation.test.ts to not test removed tools
- Update handlers-n8n-manager.test.ts error message expectations

All 399 MCP unit tests now pass.

Conceived by Romuald Członkowski - www.aiadvisors.pl/en

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: update integration tests to use valid tools after v2.25.0 removal

Replaced all references to removed tools in integration tests:
- list_nodes -> search_nodes
- get_database_statistics -> tools_documentation
- list_ai_tools -> search_nodes/tools_documentation
- list_tasks -> tools_documentation
- get_node_as_tool_info -> removed test section

Updated test files:
- tests/integration/mcp-protocol/basic-connection.test.ts
- tests/integration/mcp-protocol/performance.test.ts
- tests/integration/mcp-protocol/session-management.test.ts
- tests/integration/mcp-protocol/test-helpers.ts
- tests/integration/mcp-protocol/tool-invocation.test.ts
- tests/integration/telemetry/mcp-telemetry.test.ts
- tests/unit/mcp/disabled-tools.test.ts
- tests/unit/mcp/tools-documentation.test.ts

Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* feat: Tool consolidation v2.26.0 - reduce tools by 38% (31 → 19)

Major consolidation of MCP tools using mode-based parameters for better
AI agent ergonomics:

Node Tools:
- get_node_documentation → get_node with mode='documentation'
- search_node_properties → get_node with mode='search_properties'
- get_property_dependencies → removed

Validation Tools:
- validate_node_operation + validate_node_minimal → validate_node with mode param

Template Tools:
- list_node_templates → search_templates with searchMode='nodes'
- search_templates_by_metadata → search_templates with searchMode='metadata'
- get_templates_for_task → search_templates with searchMode='task'

Workflow Getters:
- n8n_get_workflow_details/structure/minimal → n8n_get_workflow with mode param

Execution Tools:
- n8n_list/get/delete_execution → n8n_executions with action param

Test updates for all consolidated tools.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en

* docs: comprehensive README update for v2.26.0 tool consolidation

- Quick Start: Added hosted service (dashboard.n8n-mcp.com) as primary option
- Self-hosting: Renamed options to A (npx), B (Docker), C (Local), D (Railway)
- Removed: "Memory Leak Fix (v2.20.2)" section (outdated)
- Removed: "Known Issues" section (outdated container management)
- Claude Project Setup: Updated all tool references to v2.26.0 consolidated tools
  - validate_node({mode: 'minimal'|'full'}) instead of separate tools
  - search_templates({searchMode: ...}) unified template search
  - get_node({mode: 'docs'|'search_properties'}) for documentation
  - n8n_executions({action: ...}) unified execution management
- Available MCP Tools: Updated to show 19 consolidated tools (7 core + 12 mgmt)
- Recent Updates: Simplified to just link to CHANGELOG.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en

* fix: update tool count from 31 to 19 in diagnostic message

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(tests): update tool count expectations for v2.26.0

Update handlers-n8n-manager.test.ts to expect new consolidated
tool counts (7/12/19) after v2.26.0 tool consolidation.

Conceived by Romuald Członkowski - www.aiadvisors.pl/en

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Romuald Członkowski
2025-11-25 18:39:00 +01:00
committed by GitHub
parent 9ee4b9492f
commit ff69e4ccca
28 changed files with 925 additions and 1766 deletions

View File

@@ -4,72 +4,71 @@ import { N8NDocumentationMCPServer } from '../../../src/mcp/server';
describe('Basic MCP Connection', () => {
it('should initialize MCP server', async () => {
const server = new N8NDocumentationMCPServer();
// Test executeTool directly - it returns raw data
const result = await server.executeTool('get_database_statistics', {});
// Test executeTool directly - tools_documentation returns a string
const result = await server.executeTool('tools_documentation', {});
expect(result).toBeDefined();
expect(typeof result).toBe('object');
expect(result.totalNodes).toBeDefined();
expect(result.statistics).toBeDefined();
expect(typeof result).toBe('string');
expect(result).toContain('n8n MCP');
await server.shutdown();
});
it('should execute list_nodes tool', async () => {
it('should execute search_nodes tool', async () => {
const server = new N8NDocumentationMCPServer();
// First check if we have any nodes in the database
const stats = await server.executeTool('get_database_statistics', {});
const hasNodes = stats.totalNodes > 0;
const result = await server.executeTool('list_nodes', { limit: 5 });
expect(result).toBeDefined();
expect(typeof result).toBe('object');
expect(result.nodes).toBeDefined();
expect(Array.isArray(result.nodes)).toBe(true);
if (hasNodes) {
// If database has nodes, we should get up to 5
expect(result.nodes.length).toBeLessThanOrEqual(5);
expect(result.nodes.length).toBeGreaterThan(0);
expect(result.nodes[0]).toHaveProperty('nodeType');
expect(result.nodes[0]).toHaveProperty('displayName');
} else {
// In test environment with empty database, we expect empty results
expect(result.nodes).toHaveLength(0);
try {
// Search for a common node to verify database has content
const result = await server.executeTool('search_nodes', { query: 'http', limit: 5 });
expect(result).toBeDefined();
expect(typeof result).toBe('object');
expect(result.results).toBeDefined();
expect(Array.isArray(result.results)).toBe(true);
if (result.totalCount > 0) {
// If database has nodes, we should get results
expect(result.results.length).toBeLessThanOrEqual(5);
expect(result.results.length).toBeGreaterThan(0);
expect(result.results[0]).toHaveProperty('nodeType');
expect(result.results[0]).toHaveProperty('displayName');
}
} catch (error: any) {
// In test environment with empty database, expect appropriate error
expect(error.message).toContain('Database is empty');
}
await server.shutdown();
});
it('should search nodes', async () => {
it('should search nodes by keyword', async () => {
const server = new N8NDocumentationMCPServer();
// First check if we have any nodes in the database
const stats = await server.executeTool('get_database_statistics', {});
const hasNodes = stats.totalNodes > 0;
const result = await server.executeTool('search_nodes', { query: 'webhook' });
expect(result).toBeDefined();
expect(typeof result).toBe('object');
expect(result.results).toBeDefined();
expect(Array.isArray(result.results)).toBe(true);
// Only expect results if the database has nodes
if (hasNodes) {
expect(result.results.length).toBeGreaterThan(0);
expect(result.totalCount).toBeGreaterThan(0);
// Should find webhook node
const webhookNode = result.results.find((n: any) => n.nodeType === 'nodes-base.webhook');
expect(webhookNode).toBeDefined();
expect(webhookNode.displayName).toContain('Webhook');
} else {
// In test environment with empty database, we expect empty results
expect(result.results).toHaveLength(0);
expect(result.totalCount).toBe(0);
try {
// Search to check if database has nodes
const searchResult = await server.executeTool('search_nodes', { query: 'set', limit: 1 });
const hasNodes = searchResult.totalCount > 0;
const result = await server.executeTool('search_nodes', { query: 'webhook' });
expect(result).toBeDefined();
expect(typeof result).toBe('object');
expect(result.results).toBeDefined();
expect(Array.isArray(result.results)).toBe(true);
// Only expect results if the database has nodes
if (hasNodes) {
expect(result.results.length).toBeGreaterThan(0);
expect(result.totalCount).toBeGreaterThan(0);
// Should find webhook node
const webhookNode = result.results.find((n: any) => n.nodeType === 'nodes-base.webhook');
expect(webhookNode).toBeDefined();
expect(webhookNode.displayName).toContain('Webhook');
}
} catch (error: any) {
// In test environment with empty database, expect appropriate error
expect(error.message).toContain('Database is empty');
}
await server.shutdown();
});
});

View File

@@ -84,16 +84,16 @@ describe('MCP Error Handling', () => {
describe('Tool-Specific Errors', () => {
describe('Node Discovery Errors', () => {
it('should handle invalid category filter', async () => {
const response = await client.callTool({ name: 'list_nodes', arguments: {
category: 'invalid_category'
it('should handle search with no matching results', async () => {
const response = await client.callTool({ name: 'search_nodes', arguments: {
query: 'xyznonexistentnode123'
} });
// Should return empty array, not error
const result = JSON.parse((response as any).content[0].text);
expect(result).toHaveProperty('nodes');
expect(Array.isArray(result.nodes)).toBe(true);
expect(result.nodes).toHaveLength(0);
expect(result).toHaveProperty('results');
expect(Array.isArray(result.results)).toBe(true);
expect(result.results).toHaveLength(0);
});
it('should handle invalid search mode', async () => {
@@ -135,11 +135,13 @@ describe('MCP Error Handling', () => {
});
describe('Validation Errors', () => {
// v2.26.0: validate_node_operation consolidated into validate_node
it('should handle invalid validation profile', async () => {
try {
await client.callTool({ name: 'validate_node_operation', arguments: {
await client.callTool({ name: 'validate_node', arguments: {
nodeType: 'nodes-base.httpRequest',
config: { method: 'GET', url: 'https://api.example.com' },
mode: 'full',
profile: 'invalid_profile' as any
} });
expect.fail('Should have thrown an error');
@@ -279,9 +281,9 @@ describe('MCP Error Handling', () => {
for (let i = 0; i < requestCount; i++) {
promises.push(
client.callTool({ name: 'list_nodes', arguments: {
limit: 1,
category: i % 2 === 0 ? 'trigger' : 'transform'
client.callTool({ name: 'search_nodes', arguments: {
query: i % 2 === 0 ? 'webhook' : 'http',
limit: 1
} })
);
}
@@ -292,12 +294,14 @@ describe('MCP Error Handling', () => {
});
describe('Invalid JSON Handling', () => {
// v2.26.0: validate_node_operation consolidated into validate_node
it('should handle invalid JSON in tool parameters', async () => {
try {
// Config should be an object, not a string
await client.callTool({ name: 'validate_node_operation', arguments: {
await client.callTool({ name: 'validate_node', arguments: {
nodeType: 'nodes-base.httpRequest',
config: 'invalid json string' as any
config: 'invalid json string' as any,
mode: 'full'
} });
expect.fail('Should have thrown an error');
} catch (error: any) {
@@ -320,13 +324,13 @@ describe('MCP Error Handling', () => {
describe('Timeout Scenarios', () => {
it('should handle rapid sequential requests', async () => {
const start = Date.now();
for (let i = 0; i < 20; i++) {
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'tools_documentation', arguments: {} });
}
const duration = Date.now() - start;
// Should complete reasonably quickly (under 5 seconds)
expect(duration).toBeLessThan(5000);
});
@@ -410,25 +414,25 @@ describe('MCP Error Handling', () => {
}
// Should still work
const response = await client.callTool({ name: 'list_nodes', arguments: { limit: 1 } });
const response = await client.callTool({ name: 'search_nodes', arguments: { query: 'webhook', limit: 1 } });
expect(response).toBeDefined();
});
it('should handle mixed success and failure', async () => {
const promises = [
client.callTool({ name: 'list_nodes', arguments: { limit: 5 } }),
client.callTool({ name: 'search_nodes', arguments: { query: 'webhook', limit: 5 } }),
client.callTool({ name: 'get_node', arguments: { nodeType: 'invalid' } }).catch(e => ({ error: e })),
client.callTool({ name: 'get_database_statistics', arguments: {} }),
client.callTool({ name: 'tools_documentation', arguments: {} }),
client.callTool({ name: 'search_nodes', arguments: { query: '' } }).catch(e => ({ error: e })),
client.callTool({ name: 'list_ai_tools', arguments: {} })
client.callTool({ name: 'get_node', arguments: { nodeType: 'nodes-base.httpRequest' } })
];
const results = await Promise.all(promises);
// Some should succeed, some should fail
const successes = results.filter(r => !('error' in r));
const failures = results.filter(r => 'error' in r);
expect(successes.length).toBeGreaterThan(0);
expect(failures.length).toBeGreaterThan(0);
});
@@ -436,14 +440,14 @@ describe('MCP Error Handling', () => {
describe('Edge Cases', () => {
it('should handle empty responses gracefully', async () => {
const response = await client.callTool({ name: 'list_nodes', arguments: {
category: 'nonexistent_category'
const response = await client.callTool({ name: 'search_nodes', arguments: {
query: 'xyznonexistentnode12345'
} });
const result = JSON.parse((response as any).content[0].text);
expect(result).toHaveProperty('nodes');
expect(Array.isArray(result.nodes)).toBe(true);
expect(result.nodes).toHaveLength(0);
expect(result).toHaveProperty('results');
expect(Array.isArray(result.results)).toBe(true);
expect(result.results).toHaveLength(0);
});
it('should handle special characters in parameters', async () => {
@@ -469,14 +473,15 @@ describe('MCP Error Handling', () => {
it('should handle null and undefined gracefully', async () => {
// Most tools should handle missing optional params
const response = await client.callTool({ name: 'list_nodes', arguments: {
const response = await client.callTool({ name: 'search_nodes', arguments: {
query: 'webhook',
limit: undefined as any,
category: null as any
mode: null as any
} });
const result = JSON.parse((response as any).content[0].text);
expect(result).toHaveProperty('nodes');
expect(Array.isArray(result.nodes)).toBe(true);
expect(result).toHaveProperty('results');
expect(Array.isArray(result.results)).toBe(true);
});
});
@@ -508,13 +513,15 @@ describe('MCP Error Handling', () => {
}
});
// v2.26.0: validate_node_operation consolidated into validate_node
it('should provide context for validation errors', async () => {
const response = await client.callTool({ name: 'validate_node_operation', arguments: {
const response = await client.callTool({ name: 'validate_node', arguments: {
nodeType: 'nodes-base.httpRequest',
config: {
// Missing required fields
method: 'INVALID_METHOD'
}
},
mode: 'full'
} });
const validation = JSON.parse((response as any).content[0].text);

View File

@@ -23,13 +23,13 @@ describe('MCP Performance Tests', () => {
await client.connect(clientTransport);
// Verify database is populated by checking statistics
const statsResponse = await client.callTool({ name: 'get_database_statistics', arguments: {} });
if ((statsResponse as any).content && (statsResponse as any).content[0]) {
const stats = JSON.parse((statsResponse as any).content[0].text);
// Verify database is populated by searching for a common node
const searchResponse = await client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 1 } });
if ((searchResponse as any).content && (searchResponse as any).content[0]) {
const searchResult = JSON.parse((searchResponse as any).content[0].text);
// Ensure database has nodes for testing
if (!stats.totalNodes || stats.totalNodes === 0) {
console.error('Database stats:', stats);
if (!searchResult.totalCount || searchResult.totalCount === 0) {
console.error('Search result:', searchResult);
throw new Error('Test database not properly populated');
}
}
@@ -46,13 +46,13 @@ describe('MCP Performance Tests', () => {
const start = performance.now();
for (let i = 0; i < iterations; i++) {
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'tools_documentation', arguments: {} });
}
const duration = performance.now() - start;
const avgTime = duration / iterations;
console.log(`Average response time for get_database_statistics: ${avgTime.toFixed(2)}ms`);
console.log(`Average response time for tools_documentation: ${avgTime.toFixed(2)}ms`);
console.log(`Environment: ${process.env.CI ? 'CI' : 'Local'}`);
// Environment-aware threshold (relaxed +20% for type safety overhead)
@@ -60,20 +60,20 @@ describe('MCP Performance Tests', () => {
expect(avgTime).toBeLessThan(threshold);
});
it('should handle list operations efficiently', async () => {
it('should handle search operations efficiently', async () => {
const iterations = 50;
const start = performance.now();
for (let i = 0; i < iterations; i++) {
await client.callTool({ name: 'list_nodes', arguments: { limit: 10 } });
await client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 10 } });
}
const duration = performance.now() - start;
const avgTime = duration / iterations;
console.log(`Average response time for list_nodes: ${avgTime.toFixed(2)}ms`);
console.log(`Average response time for search_nodes: ${avgTime.toFixed(2)}ms`);
console.log(`Environment: ${process.env.CI ? 'CI' : 'Local'}`);
// Environment-aware threshold
const threshold = process.env.CI ? 40 : 20;
expect(avgTime).toBeLessThan(threshold);
@@ -137,7 +137,7 @@ describe('MCP Performance Tests', () => {
const promises = [];
for (let i = 0; i < concurrentRequests; i++) {
promises.push(
client.callTool({ name: 'list_nodes', arguments: { limit: 5 } })
client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 5 } })
);
}
@@ -148,7 +148,7 @@ describe('MCP Performance Tests', () => {
console.log(`Average time for ${concurrentRequests} concurrent requests: ${avgTime.toFixed(2)}ms`);
console.log(`Environment: ${process.env.CI ? 'CI' : 'Local'}`);
// Concurrent requests should be more efficient than sequential
const threshold = process.env.CI ? 25 : 10;
expect(avgTime).toBeLessThan(threshold);
@@ -156,11 +156,11 @@ describe('MCP Performance Tests', () => {
it('should handle mixed concurrent operations', async () => {
const operations = [
{ tool: 'list_nodes', params: { limit: 10 } },
{ tool: 'search_nodes', params: { query: 'http' } },
{ tool: 'get_database_statistics', params: {} },
{ tool: 'list_ai_tools', params: {} },
{ tool: 'list_tasks', params: {} }
{ tool: 'search_nodes', params: { query: 'http', limit: 10 } },
{ tool: 'search_nodes', params: { query: 'webhook' } },
{ tool: 'tools_documentation', params: {} },
{ tool: 'get_node', params: { nodeType: 'nodes-base.httpRequest' } },
{ tool: 'get_node', params: { nodeType: 'nodes-base.webhook' } }
];
const rounds = 10;
@@ -186,34 +186,35 @@ describe('MCP Performance Tests', () => {
});
describe('Large Data Performance', () => {
it('should handle large node lists efficiently', async () => {
it('should handle large search results efficiently', async () => {
const start = performance.now();
const response = await client.callTool({ name: 'list_nodes', arguments: {
limit: 200 // Get many nodes
const response = await client.callTool({ name: 'search_nodes', arguments: {
query: 'n8n', // Broad query to get many results
limit: 200
} });
const duration = performance.now() - start;
console.log(`Time to list 200 nodes: ${duration.toFixed(2)}ms`);
console.log(`Time to search 200 nodes: ${duration.toFixed(2)}ms`);
// Environment-aware threshold
const threshold = process.env.CI ? 200 : 100;
expect(duration).toBeLessThan(threshold);
// Check the response content
expect(response).toBeDefined();
let nodes;
let results;
if (response.content && Array.isArray(response.content) && response.content[0]) {
// MCP standard response format
expect(response.content[0].type).toBe('text');
expect(response.content[0].text).toBeDefined();
try {
const parsed = JSON.parse(response.content[0].text);
// list_nodes returns an object with nodes property
nodes = parsed.nodes || parsed;
// search_nodes returns an object with results property
results = parsed.results || parsed;
} catch (e) {
console.error('Failed to parse JSON:', e);
console.error('Response text was:', response.content[0].text);
@@ -221,18 +222,18 @@ describe('MCP Performance Tests', () => {
}
} else if (Array.isArray(response)) {
// Direct array response
nodes = response;
} else if (response.nodes) {
// Object with nodes property
nodes = response.nodes;
results = response;
} else if (response.results) {
// Object with results property
results = response.results;
} else {
console.error('Unexpected response format:', response);
throw new Error('Unexpected response format');
}
expect(nodes).toBeDefined();
expect(Array.isArray(nodes)).toBe(true);
expect(nodes.length).toBeGreaterThan(100);
expect(results).toBeDefined();
expect(Array.isArray(results)).toBe(true);
expect(results.length).toBeGreaterThan(50);
});
it('should handle large workflow validation efficiently', async () => {
@@ -301,10 +302,10 @@ describe('MCP Performance Tests', () => {
for (let i = 0; i < iterations; i += batchSize) {
const promises = [];
for (let j = 0; j < batchSize; j++) {
promises.push(
client.callTool({ name: 'get_database_statistics', arguments: {} })
client.callTool({ name: 'tools_documentation', arguments: {} })
);
}
@@ -330,9 +331,9 @@ describe('MCP Performance Tests', () => {
// Perform large operations
for (let i = 0; i < 10; i++) {
await client.callTool({ name: 'list_nodes', arguments: { limit: 200 } });
await client.callTool({ name: 'get_node', arguments: {
nodeType: 'nodes-base.httpRequest'
await client.callTool({ name: 'search_nodes', arguments: { query: 'n8n', limit: 200 } });
await client.callTool({ name: 'get_node', arguments: {
nodeType: 'nodes-base.httpRequest'
} });
}
@@ -359,16 +360,16 @@ describe('MCP Performance Tests', () => {
for (const load of loadLevels) {
const start = performance.now();
const promises = [];
for (let i = 0; i < load; i++) {
promises.push(
client.callTool({ name: 'list_nodes', arguments: { limit: 1 } })
client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 1 } })
);
}
await Promise.all(promises);
const duration = performance.now() - start;
const avgTime = duration / load;
@@ -384,10 +385,10 @@ describe('MCP Performance Tests', () => {
// Average time should not increase dramatically with load
const firstAvg = results[0].avgTime;
const lastAvg = results[results.length - 1].avgTime;
console.log(`Environment: ${process.env.CI ? 'CI' : 'Local'}`);
console.log(`Performance scaling - First avg: ${firstAvg.toFixed(2)}ms, Last avg: ${lastAvg.toFixed(2)}ms`);
// Environment-aware scaling factor
const scalingFactor = process.env.CI ? 3 : 2;
expect(lastAvg).toBeLessThan(firstAvg * scalingFactor);
@@ -403,16 +404,16 @@ describe('MCP Performance Tests', () => {
const operation = i % 4;
switch (operation) {
case 0:
promises.push(client.callTool({ name: 'list_nodes', arguments: { limit: 5 } }));
promises.push(client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 5 } }));
break;
case 1:
promises.push(client.callTool({ name: 'search_nodes', arguments: { query: 'test' } }));
break;
case 2:
promises.push(client.callTool({ name: 'get_database_statistics', arguments: {} }));
promises.push(client.callTool({ name: 'tools_documentation', arguments: {} }));
break;
case 3:
promises.push(client.callTool({ name: 'list_ai_tools', arguments: {} }));
promises.push(client.callTool({ name: 'get_node', arguments: { nodeType: 'nodes-base.set' } }));
break;
}
}
@@ -431,10 +432,10 @@ describe('MCP Performance Tests', () => {
});
describe('Critical Path Optimization', () => {
it('should optimize tool listing performance', async () => {
it('should optimize search performance', async () => {
// Warm up with multiple calls to ensure everything is initialized
for (let i = 0; i < 5; i++) {
await client.callTool({ name: 'list_nodes', arguments: { limit: 1 } });
await client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 1 } });
}
const iterations = 100;
@@ -442,32 +443,32 @@ describe('MCP Performance Tests', () => {
for (let i = 0; i < iterations; i++) {
const start = performance.now();
await client.callTool({ name: 'list_nodes', arguments: { limit: 20 } });
await client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 20 } });
times.push(performance.now() - start);
}
// Remove outliers (first few runs might be slower)
times.sort((a, b) => a - b);
const trimmedTimes = times.slice(10, -10); // Remove top and bottom 10%
const avgTime = trimmedTimes.reduce((a, b) => a + b, 0) / trimmedTimes.length;
const minTime = Math.min(...trimmedTimes);
const maxTime = Math.max(...trimmedTimes);
console.log(`list_nodes performance - Avg: ${avgTime.toFixed(2)}ms, Min: ${minTime.toFixed(2)}ms, Max: ${maxTime.toFixed(2)}ms`);
console.log(`search_nodes performance - Avg: ${avgTime.toFixed(2)}ms, Min: ${minTime.toFixed(2)}ms, Max: ${maxTime.toFixed(2)}ms`);
console.log(`Environment: ${process.env.CI ? 'CI' : 'Local'}`);
// Environment-aware thresholds
const threshold = process.env.CI ? 25 : 10;
expect(avgTime).toBeLessThan(threshold);
// Max should not be too much higher than average (no outliers)
// More lenient in CI due to resource contention
const maxMultiplier = process.env.CI ? 5 : 3;
expect(maxTime).toBeLessThan(avgTime * maxMultiplier);
});
it('should optimize search performance', async () => {
it('should handle varied search queries efficiently', async () => {
// Warm up with multiple calls
for (let i = 0; i < 3; i++) {
await client.callTool({ name: 'search_nodes', arguments: { query: 'test' } });
@@ -487,7 +488,7 @@ describe('MCP Performance Tests', () => {
// Remove outliers
times.sort((a, b) => a - b);
const trimmedTimes = times.slice(10, -10); // Remove top and bottom 10%
const avgTime = trimmedTimes.reduce((a, b) => a + b, 0) / trimmedTimes.length;
console.log(`search_nodes average performance: ${avgTime.toFixed(2)}ms`);
@@ -542,7 +543,7 @@ describe('MCP Performance Tests', () => {
while (performance.now() - start < duration) {
try {
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'tools_documentation', arguments: {} });
requestCount++;
} catch (error) {
errorCount++;
@@ -559,7 +560,7 @@ describe('MCP Performance Tests', () => {
// Relaxed to 75 RPS locally to account for parallel test execution overhead
const rpsThreshold = process.env.CI ? 50 : 75;
expect(requestsPerSecond).toBeGreaterThan(rpsThreshold);
// Error rate should be very low
expect(errorCount).toBe(0);
});
@@ -591,7 +592,7 @@ describe('MCP Performance Tests', () => {
const recoveryTimes: number[] = [];
for (let i = 0; i < 10; i++) {
const start = performance.now();
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'tools_documentation', arguments: {} });
recoveryTimes.push(performance.now() - start);
}

View File

@@ -74,7 +74,7 @@ describe('MCP Protocol Compliance', () => {
for (let i = 0; i < 5; i++) {
expectedOrder.push(i);
requests.push(
client.callTool({ name: 'get_database_statistics', arguments: {} })
client.callTool({ name: 'tools_documentation', arguments: {} })
.then(() => i)
);
}
@@ -125,7 +125,7 @@ describe('MCP Protocol Compliance', () => {
it('should handle missing params gracefully', async () => {
// Most tools should work without params
const response = await client.callTool({ name: 'list_nodes', arguments: {} });
const response = await client.callTool({ name: 'search_nodes', arguments: { query: 'webhook' } });
expect(response).toBeDefined();
});
@@ -147,8 +147,8 @@ describe('MCP Protocol Compliance', () => {
describe('Content Types', () => {
it('should handle text content in tool responses', async () => {
const response = await client.callTool({ name: 'get_database_statistics', arguments: {} });
const response = await client.callTool({ name: 'tools_documentation', arguments: {} });
expect((response as any).content).toHaveLength(1);
expect((response as any).content[0]).toHaveProperty('type', 'text');
expect((response as any).content[0]).toHaveProperty('text');
@@ -167,14 +167,15 @@ describe('MCP Protocol Compliance', () => {
});
it('should handle JSON content properly', async () => {
const response = await client.callTool({ name: 'list_nodes', arguments: {
const response = await client.callTool({ name: 'search_nodes', arguments: {
query: 'webhook',
limit: 5
} });
expect((response as any).content).toHaveLength(1);
const content = JSON.parse((response as any).content[0].text);
expect(content).toHaveProperty('nodes');
expect(Array.isArray(content.nodes)).toBe(true);
expect(content).toHaveProperty('results');
expect(Array.isArray(content.results)).toBe(true);
});
});
@@ -197,10 +198,10 @@ describe('MCP Protocol Compliance', () => {
const results: string[] = [];
// Start multiple requests with different delays
const p1 = client.callTool({ name: 'get_database_statistics', arguments: {} })
.then(() => { results.push('stats'); return 'stats'; });
const p1 = client.callTool({ name: 'tools_documentation', arguments: {} })
.then(() => { results.push('docs'); return 'docs'; });
const p2 = client.callTool({ name: 'list_nodes', arguments: { limit: 1 } })
const p2 = client.callTool({ name: 'search_nodes', arguments: { query: 'webhook', limit: 1 } })
.then(() => { results.push('nodes'); return 'nodes'; });
const p3 = client.callTool({ name: 'search_nodes', arguments: { query: 'http' } })
@@ -216,13 +217,14 @@ describe('MCP Protocol Compliance', () => {
describe('Protocol Extensions', () => {
it('should handle tool-specific extensions', async () => {
// Test tool with complex params
const response = await client.callTool({ name: 'validate_node_operation', arguments: {
// Test tool with complex params (using consolidated validate_node from v2.26.0)
const response = await client.callTool({ name: 'validate_node', arguments: {
nodeType: 'nodes-base.httpRequest',
config: {
method: 'GET',
url: 'https://api.example.com'
},
mode: 'full',
profile: 'runtime'
} });
@@ -232,13 +234,13 @@ describe('MCP Protocol Compliance', () => {
it('should support optional parameters', async () => {
// Call with minimal params
const response1 = await client.callTool({ name: 'list_nodes', arguments: {} });
const response1 = await client.callTool({ name: 'search_nodes', arguments: { query: 'webhook' } });
// Call with all params
const response2 = await client.callTool({ name: 'list_nodes', arguments: {
const response2 = await client.callTool({ name: 'search_nodes', arguments: {
query: 'webhook',
limit: 10,
category: 'trigger',
package: 'n8n-nodes-base'
mode: 'OR'
} });
expect(response1).toBeDefined();
@@ -255,7 +257,7 @@ describe('MCP Protocol Compliance', () => {
await testClient.connect(clientTransport);
// Make a request
const response = await testClient.callTool({ name: 'get_database_statistics', arguments: {} });
const response = await testClient.callTool({ name: 'tools_documentation', arguments: {} });
expect(response).toBeDefined();
// Close client
@@ -263,7 +265,7 @@ describe('MCP Protocol Compliance', () => {
// Further requests should fail
try {
await testClient.callTool({ name: 'get_database_statistics', arguments: {} });
await testClient.callTool({ name: 'tools_documentation', arguments: {} });
expect.fail('Should have thrown an error');
} catch (error) {
expect(error).toBeDefined();
@@ -286,7 +288,7 @@ describe('MCP Protocol Compliance', () => {
const testClient = new Client({ name: 'test', version: '1.0.0' }, {});
await testClient.connect(clientTransport);
const response = await testClient.callTool({ name: 'get_database_statistics', arguments: {} });
const response = await testClient.callTool({ name: 'tools_documentation', arguments: {} });
expect(response).toBeDefined();
await testClient.close();

View File

@@ -100,8 +100,8 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
await client.connect(clientTransport);
// Make some requests
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'list_nodes', arguments: { limit: 5 } });
await client.callTool({ name: 'tools_documentation', arguments: {} });
await client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 5 } });
// Clean termination
await client.close();
@@ -109,7 +109,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
// Client should be closed
try {
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'tools_documentation', arguments: {} });
expect.fail('Should not be able to make requests after close');
} catch (error) {
expect(error).toBeDefined();
@@ -133,7 +133,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
await client.connect(clientTransport);
// Make a request to ensure connection is active
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'tools_documentation', arguments: {} });
// Simulate abrupt disconnection by closing transport
await clientTransport.close();
@@ -141,7 +141,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
// Further operations should fail
try {
await client.callTool({ name: 'list_nodes', arguments: {} });
await client.callTool({ name: 'search_nodes', arguments: { query: 'http' } });
expect.fail('Should not be able to make requests after transport close');
} catch (error) {
expect(error).toBeDefined();
@@ -179,14 +179,14 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
await client1.connect(ct1);
// First session operations
const response1 = await client1.callTool({ name: 'list_nodes', arguments: { limit: 3 } });
const response1 = await client1.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 3 } });
expect(response1).toBeDefined();
expect((response1 as any).content).toBeDefined();
expect((response1 as any).content[0]).toHaveProperty('type', 'text');
const data1 = JSON.parse(((response1 as any).content[0] as any).text);
// Handle both array response and object with nodes property
const nodes1 = Array.isArray(data1) ? data1 : data1.nodes;
expect(nodes1).toHaveLength(3);
// Handle both array response and object with results property
const results1 = Array.isArray(data1) ? data1 : data1.results;
expect(results1.length).toBeLessThanOrEqual(3);
// Close first session completely
await client1.close();
@@ -204,14 +204,14 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
await client2.connect(ct2);
// Second session operations
const response2 = await client2.callTool({ name: 'list_nodes', arguments: { limit: 5 } });
const response2 = await client2.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 5 } });
expect(response2).toBeDefined();
expect((response2 as any).content).toBeDefined();
expect((response2 as any).content[0]).toHaveProperty('type', 'text');
const data2 = JSON.parse(((response2 as any).content[0] as any).text);
// Handle both array response and object with nodes property
const nodes2 = Array.isArray(data2) ? data2 : data2.nodes;
expect(nodes2).toHaveLength(5);
// Handle both array response and object with results property
const results2 = Array.isArray(data2) ? data2 : data2.results;
expect(results2.length).toBeLessThanOrEqual(5);
// Clean up
await client2.close();
@@ -228,9 +228,9 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
const client1 = new Client({ name: 'multi-seq-1', version: '1.0.0' }, {});
await client1.connect(ct1);
const resp1 = await client1.callTool({ name: 'get_database_statistics', arguments: {} });
const resp1 = await client1.callTool({ name: 'tools_documentation', arguments: {} });
expect(resp1).toBeDefined();
await client1.close();
await new Promise(resolve => setTimeout(resolve, 50));
@@ -239,8 +239,8 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
await mcpServer.connectToTransport(st2);
const client2 = new Client({ name: 'multi-seq-2', version: '1.0.0' }, {});
await client2.connect(ct2);
const resp2 = await client2.callTool({ name: 'get_database_statistics', arguments: {} });
const resp2 = await client2.callTool({ name: 'tools_documentation', arguments: {} });
expect(resp2).toBeDefined();
await client2.close();
@@ -261,14 +261,14 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
await client1.connect(ct1);
// Make some requests
await client1.callTool({ name: 'list_nodes', arguments: { limit: 10 } });
await client1.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 10 } });
await client1.close();
await mcpServer1.close();
// Second session - should be fresh
const mcpServer2 = new TestableN8NMCPServer();
await mcpServer2.initialize();
const [st2, ct2] = InMemoryTransport.createLinkedPair();
await mcpServer2.connectToTransport(st2);
@@ -276,7 +276,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
await client2.connect(ct2);
// Should work normally
const response = await client2.callTool({ name: 'get_database_statistics', arguments: {} });
const response = await client2.callTool({ name: 'tools_documentation', arguments: {} });
expect(response).toBeDefined();
await client2.close();
@@ -299,7 +299,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
await client.connect(clientTransport);
// Quick operation
const response = await client.callTool({ name: 'get_database_statistics', arguments: {} });
const response = await client.callTool({ name: 'tools_documentation', arguments: {} });
expect(response).toBeDefined();
// Explicit cleanup for each iteration
@@ -392,7 +392,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
// Light operation
if (i % 10 === 0) {
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'tools_documentation', arguments: {} });
}
// Explicit cleanup
@@ -420,8 +420,8 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
const promises = [];
for (let i = 0; i < requestCount; i++) {
const toolName = i % 2 === 0 ? 'list_nodes' : 'get_database_statistics';
const params = toolName === 'list_nodes' ? { limit: 1 } : {};
const toolName = i % 2 === 0 ? 'search_nodes' : 'tools_documentation';
const params = toolName === 'search_nodes' ? { query: 'http', limit: 1 } : {};
promises.push(client.callTool({ name: toolName as any, arguments: params }));
}
@@ -460,9 +460,9 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
}
// Session should still be active
const response = await client.callTool({ name: 'get_database_statistics', arguments: {} });
const response = await client.callTool({ name: 'tools_documentation', arguments: {} });
expect(response).toBeDefined();
await client.close();
await new Promise(resolve => setTimeout(resolve, 50)); // Give time for client to fully close
await mcpServer.close();
@@ -496,9 +496,9 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
});
// Session should still work
const response = await client.callTool({ name: 'list_nodes', arguments: { limit: 1 } });
const response = await client.callTool({ name: 'search_nodes', arguments: { query: 'http', limit: 1 } });
expect(response).toBeDefined();
await client.close();
await new Promise(resolve => setTimeout(resolve, 50)); // Give time for client to fully close
await mcpServer.close();
@@ -539,7 +539,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
resources.clients.push(client);
// Make a request to ensure connection is active
await client.callTool({ name: 'get_database_statistics', arguments: {} });
await client.callTool({ name: 'tools_documentation', arguments: {} });
}
// Verify all resources are active
@@ -586,7 +586,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
// 3. Verify cleanup by attempting operations (should fail)
for (let i = 0; i < resources.clients.length; i++) {
try {
await resources.clients[i].callTool({ name: 'get_database_statistics', arguments: {} });
await resources.clients[i].callTool({ name: 'tools_documentation', arguments: {} });
expect.fail('Client should be closed');
} catch (error) {
// Expected - client is closed
@@ -643,9 +643,9 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
}, {});
await client.connect(ct1);
// Initial request
const response1 = await client.callTool({ name: 'get_database_statistics', arguments: {} });
const response1 = await client.callTool({ name: 'tools_documentation', arguments: {} });
expect(response1).toBeDefined();
// Close first client
@@ -654,7 +654,7 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
// New connection with same server
const [st2, ct2] = InMemoryTransport.createLinkedPair();
const connectTimeout = setTimeout(() => {
throw new Error('Second connection timeout');
}, 3000);
@@ -673,14 +673,14 @@ describe('MCP Session Management', { timeout: 15000 }, () => {
}, {});
await newClient.connect(ct2);
// Should work normally
const callTimeout = setTimeout(() => {
throw new Error('Second call timeout');
}, 3000);
try {
const response2 = await newClient.callTool({ name: 'get_database_statistics', arguments: {} });
const response2 = await newClient.callTool({ name: 'tools_documentation', arguments: {} });
clearTimeout(callTimeout);
expect(response2).toBeDefined();
} catch (error) {

View File

@@ -114,7 +114,7 @@ export class TestableN8NMCPServer {
// The MCP server initializes its database lazily
// We can trigger initialization by calling executeTool
try {
await this.mcpServer.executeTool('get_database_statistics', {});
await this.mcpServer.executeTool('tools_documentation', {});
} catch (error) {
// Ignore errors, we just want to trigger initialization
}

View File

@@ -30,66 +30,6 @@ describe('MCP Tool Invocation', () => {
});
describe('Node Discovery Tools', () => {
describe('list_nodes', () => {
it('should list nodes with default parameters', async () => {
const response = await client.callTool({ name: 'list_nodes', arguments: {} });
expect((response as any).content).toHaveLength(1);
expect((response as any).content[0].type).toBe('text');
const result = JSON.parse(((response as any).content[0]).text);
// The result is an object with nodes array and totalCount
expect(result).toHaveProperty('nodes');
expect(result).toHaveProperty('totalCount');
const nodes = result.nodes;
expect(Array.isArray(nodes)).toBe(true);
expect(nodes.length).toBeGreaterThan(0);
// Check node structure
const firstNode = nodes[0];
expect(firstNode).toHaveProperty('nodeType');
expect(firstNode).toHaveProperty('displayName');
expect(firstNode).toHaveProperty('category');
});
it('should filter nodes by category', async () => {
const response = await client.callTool({ name: 'list_nodes', arguments: {
category: 'trigger'
}});
const result = JSON.parse(((response as any).content[0]).text);
const nodes = result.nodes;
expect(nodes.length).toBeGreaterThan(0);
nodes.forEach((node: any) => {
expect(node.category).toBe('trigger');
});
});
it('should limit results', async () => {
const response = await client.callTool({ name: 'list_nodes', arguments: {
limit: 5
}});
const result = JSON.parse(((response as any).content[0]).text);
const nodes = result.nodes;
expect(nodes).toHaveLength(5);
});
it('should filter by package', async () => {
const response = await client.callTool({ name: 'list_nodes', arguments: {
package: 'n8n-nodes-base'
}});
const result = JSON.parse(((response as any).content[0]).text);
const nodes = result.nodes;
expect(nodes.length).toBeGreaterThan(0);
nodes.forEach((node: any) => {
expect(node.package).toBe('n8n-nodes-base');
});
});
});
describe('search_nodes', () => {
it('should search nodes by keyword', async () => {
const response = await client.callTool({ name: 'search_nodes', arguments: {
@@ -211,14 +151,16 @@ describe('MCP Tool Invocation', () => {
});
describe('Validation Tools', () => {
describe('validate_node_operation', () => {
// v2.26.0: validate_node_operation consolidated into validate_node with mode parameter
describe('validate_node', () => {
it('should validate valid node configuration', async () => {
const response = await client.callTool({ name: 'validate_node_operation', arguments: {
const response = await client.callTool({ name: 'validate_node', arguments: {
nodeType: 'nodes-base.httpRequest',
config: {
method: 'GET',
url: 'https://api.example.com/data'
}
},
mode: 'full'
}});
const validation = JSON.parse(((response as any).content[0]).text);
@@ -228,12 +170,13 @@ describe('MCP Tool Invocation', () => {
});
it('should detect missing required fields', async () => {
const response = await client.callTool({ name: 'validate_node_operation', arguments: {
const response = await client.callTool({ name: 'validate_node', arguments: {
nodeType: 'nodes-base.httpRequest',
config: {
method: 'GET'
// Missing required 'url' field
}
},
mode: 'full'
}});
const validation = JSON.parse(((response as any).content[0]).text);
@@ -244,11 +187,12 @@ describe('MCP Tool Invocation', () => {
it('should support different validation profiles', async () => {
const profiles = ['minimal', 'runtime', 'ai-friendly', 'strict'];
for (const profile of profiles) {
const response = await client.callTool({ name: 'validate_node_operation', arguments: {
const response = await client.callTool({ name: 'validate_node', arguments: {
nodeType: 'nodes-base.httpRequest',
config: { method: 'GET', url: 'https://api.example.com' },
mode: 'full',
profile
}});
@@ -427,85 +371,8 @@ describe('MCP Tool Invocation', () => {
});
});
describe('AI Tools', () => {
describe('list_ai_tools', () => {
it('should list AI-capable nodes', async () => {
const response = await client.callTool({ name: 'list_ai_tools', arguments: {} });
const result = JSON.parse(((response as any).content[0]).text);
expect(result).toHaveProperty('tools');
const aiTools = result.tools;
expect(Array.isArray(aiTools)).toBe(true);
expect(aiTools.length).toBeGreaterThan(0);
// All should have nodeType and displayName
aiTools.forEach((tool: any) => {
expect(tool).toHaveProperty('nodeType');
expect(tool).toHaveProperty('displayName');
});
});
});
describe('get_node_as_tool_info', () => {
it('should provide AI tool usage information', async () => {
const response = await client.callTool({ name: 'get_node_as_tool_info', arguments: {
nodeType: 'nodes-base.slack'
}});
const info = JSON.parse(((response as any).content[0]).text);
expect(info).toHaveProperty('nodeType');
expect(info).toHaveProperty('isMarkedAsAITool');
expect(info).toHaveProperty('aiToolCapabilities');
expect(info.aiToolCapabilities).toHaveProperty('commonUseCases');
});
});
});
describe('Task Templates', () => {
// get_node_for_task was removed in v2.15.0
// Use search_nodes({ includeExamples: true }) instead for real-world examples
describe('list_tasks', () => {
it('should list all available tasks', async () => {
const response = await client.callTool({ name: 'list_tasks', arguments: {} });
const result = JSON.parse(((response as any).content[0]).text);
expect(result).toHaveProperty('totalTasks');
expect(result).toHaveProperty('categories');
expect(result.totalTasks).toBeGreaterThan(0);
// Check categories structure
const categories = result.categories;
expect(typeof categories).toBe('object');
// Check at least one category has tasks
const hasTasksInCategories = Object.values(categories).some((tasks: any) =>
Array.isArray(tasks) && tasks.length > 0
);
expect(hasTasksInCategories).toBe(true);
});
it('should filter by category', async () => {
const response = await client.callTool({ name: 'list_tasks', arguments: {
category: 'HTTP/API'
}});
const result = JSON.parse(((response as any).content[0]).text);
expect(result).toHaveProperty('category', 'HTTP/API');
expect(result).toHaveProperty('tasks');
const httpTasks = result.tasks;
expect(Array.isArray(httpTasks)).toBe(true);
expect(httpTasks.length).toBeGreaterThan(0);
httpTasks.forEach((task: any) => {
expect(task).toHaveProperty('task');
expect(task).toHaveProperty('description');
expect(task).toHaveProperty('nodeType');
});
});
});
});
// AI Tools section removed - list_ai_tools and get_node_as_tool_info were removed in v2.25.0
// Use search_nodes with query for finding AI-capable nodes
describe('Complex Tool Interactions', () => {
it('should handle tool chaining', async () => {
@@ -526,20 +393,20 @@ describe('MCP Tool Invocation', () => {
});
it('should handle parallel tool calls', async () => {
const tools = [
'list_nodes',
'get_database_statistics',
'list_ai_tools',
'list_tasks'
const toolCalls = [
{ name: 'search_nodes', arguments: { query: 'http' } },
{ name: 'tools_documentation', arguments: {} },
{ name: 'get_node', arguments: { nodeType: 'nodes-base.httpRequest' } },
{ name: 'search_nodes', arguments: { query: 'webhook' } }
];
const promises = tools.map(tool =>
client.callTool({ name: tool as any, arguments: {} })
const promises = toolCalls.map(call =>
client.callTool(call)
);
const responses = await Promise.all(promises);
expect(responses).toHaveLength(tools.length);
expect(responses).toHaveLength(toolCalls.length);
responses.forEach(response => {
expect(response.content).toHaveLength(1);
expect(((response as any).content[0]).type).toBe('text');

View File

@@ -1,207 +0,0 @@
/**
* Integration Tests: handleListAvailableTools
*
* Tests tool listing functionality.
* Covers tool discovery and configuration status.
*/
import { describe, it, expect, beforeEach } from 'vitest';
import { createMcpContext } from '../utils/mcp-context';
import { InstanceContext } from '../../../../src/types/instance-context';
import { handleListAvailableTools } from '../../../../src/mcp/handlers-n8n-manager';
import { ListToolsResponse } from '../utils/response-types';
describe('Integration: handleListAvailableTools', () => {
let mcpContext: InstanceContext;
beforeEach(() => {
mcpContext = createMcpContext();
});
// ======================================================================
// List All Tools
// ======================================================================
describe('Tool Listing', () => {
it('should list all available tools organized by category', async () => {
const response = await handleListAvailableTools(mcpContext);
expect(response.success).toBe(true);
expect(response.data).toBeDefined();
const data = response.data as ListToolsResponse;
// Verify tools array exists
expect(data).toHaveProperty('tools');
expect(Array.isArray(data.tools)).toBe(true);
expect(data.tools.length).toBeGreaterThan(0);
// Verify tool categories
const categories = data.tools.map((cat: any) => cat.category);
expect(categories).toContain('Workflow Management');
expect(categories).toContain('Execution Management');
expect(categories).toContain('System');
// Verify each category has tools
data.tools.forEach(category => {
expect(category).toHaveProperty('category');
expect(category).toHaveProperty('tools');
expect(Array.isArray(category.tools)).toBe(true);
expect(category.tools.length).toBeGreaterThan(0);
// Verify each tool has required fields
category.tools.forEach(tool => {
expect(tool).toHaveProperty('name');
expect(tool).toHaveProperty('description');
expect(typeof tool.name).toBe('string');
expect(typeof tool.description).toBe('string');
});
});
});
it('should include API configuration status', async () => {
const response = await handleListAvailableTools(mcpContext);
expect(response.success).toBe(true);
const data = response.data as ListToolsResponse;
// Verify configuration status
expect(data).toHaveProperty('apiConfigured');
expect(typeof data.apiConfigured).toBe('boolean');
// Since tests run with API configured, should be true
expect(data.apiConfigured).toBe(true);
// Verify configuration details are present when configured
if (data.apiConfigured) {
expect(data).toHaveProperty('configuration');
expect(data.configuration).toBeDefined();
expect(data.configuration).toHaveProperty('apiUrl');
expect(data.configuration).toHaveProperty('timeout');
expect(data.configuration).toHaveProperty('maxRetries');
}
});
it('should include API limitations information', async () => {
const response = await handleListAvailableTools(mcpContext);
expect(response.success).toBe(true);
const data = response.data as ListToolsResponse;
// Verify limitations are documented
expect(data).toHaveProperty('limitations');
expect(Array.isArray(data.limitations)).toBe(true);
expect(data.limitations.length).toBeGreaterThan(0);
// Verify limitations are informative strings
data.limitations.forEach(limitation => {
expect(typeof limitation).toBe('string');
expect(limitation.length).toBeGreaterThan(0);
});
// Common known limitations
const limitationsText = data.limitations.join(' ');
expect(limitationsText).toContain('Cannot execute workflows directly');
});
});
// ======================================================================
// Workflow Management Tools
// ======================================================================
describe('Workflow Management Tools', () => {
it('should include all workflow management tools', async () => {
const response = await handleListAvailableTools(mcpContext);
const data = response.data as ListToolsResponse;
const workflowCategory = data.tools.find(cat => cat.category === 'Workflow Management');
expect(workflowCategory).toBeDefined();
const toolNames = workflowCategory!.tools.map(t => t.name);
// Core workflow tools
expect(toolNames).toContain('n8n_create_workflow');
expect(toolNames).toContain('n8n_get_workflow');
expect(toolNames).toContain('n8n_update_workflow');
expect(toolNames).toContain('n8n_delete_workflow');
expect(toolNames).toContain('n8n_list_workflows');
// Enhanced workflow tools
expect(toolNames).toContain('n8n_get_workflow_details');
expect(toolNames).toContain('n8n_get_workflow_structure');
expect(toolNames).toContain('n8n_get_workflow_minimal');
expect(toolNames).toContain('n8n_validate_workflow');
expect(toolNames).toContain('n8n_autofix_workflow');
});
});
// ======================================================================
// Execution Management Tools
// ======================================================================
describe('Execution Management Tools', () => {
it('should include all execution management tools', async () => {
const response = await handleListAvailableTools(mcpContext);
const data = response.data as ListToolsResponse;
const executionCategory = data.tools.find(cat => cat.category === 'Execution Management');
expect(executionCategory).toBeDefined();
const toolNames = executionCategory!.tools.map(t => t.name);
expect(toolNames).toContain('n8n_trigger_webhook_workflow');
expect(toolNames).toContain('n8n_get_execution');
expect(toolNames).toContain('n8n_list_executions');
expect(toolNames).toContain('n8n_delete_execution');
});
});
// ======================================================================
// System Tools
// ======================================================================
describe('System Tools', () => {
it('should include system tools', async () => {
const response = await handleListAvailableTools(mcpContext);
const data = response.data as ListToolsResponse;
const systemCategory = data.tools.find(cat => cat.category === 'System');
expect(systemCategory).toBeDefined();
const toolNames = systemCategory!.tools.map(t => t.name);
expect(toolNames).toContain('n8n_health_check');
expect(toolNames).toContain('n8n_list_available_tools');
});
});
// ======================================================================
// Response Format Verification
// ======================================================================
describe('Response Format', () => {
it('should return complete tool list response structure', async () => {
const response = await handleListAvailableTools(mcpContext);
expect(response.success).toBe(true);
expect(response.data).toBeDefined();
const data = response.data as ListToolsResponse;
// Verify all required fields
expect(data).toHaveProperty('tools');
expect(data).toHaveProperty('apiConfigured');
expect(data).toHaveProperty('limitations');
// Verify optional configuration field
if (data.apiConfigured) {
expect(data).toHaveProperty('configuration');
}
// Verify data types
expect(Array.isArray(data.tools)).toBe(true);
expect(typeof data.apiConfigured).toBe('boolean');
expect(Array.isArray(data.limitations)).toBe(true);
});
});
});

View File

@@ -19,29 +19,6 @@ export interface HealthCheckResponse {
[key: string]: any; // Allow dynamic property access for optional field checks
}
export interface ToolDefinition {
name: string;
description: string;
}
export interface ToolCategory {
category: string;
tools: ToolDefinition[];
}
export interface ApiConfiguration {
apiUrl: string;
timeout: number;
maxRetries: number;
}
export interface ListToolsResponse {
tools: ToolCategory[];
apiConfigured: boolean;
configuration?: ApiConfiguration | null;
limitations: string[];
}
export interface ApiStatus {
configured: boolean;
connected: boolean;

View File

@@ -500,15 +500,15 @@ describe.skip('MCP Telemetry Integration', () => {
const slowToolRequest: CallToolRequest = {
method: 'tools/call',
params: {
name: 'list_nodes',
arguments: { limit: 1000 }
name: 'search_nodes',
arguments: { query: 'http', limit: 1000 }
}
};
// Mock a slow operation
vi.spyOn(mcpServer as any, 'executeTool').mockImplementation(async () => {
await new Promise(resolve => setTimeout(resolve, 2000)); // 2 second delay
return { nodes: [], totalCount: 0 };
return { results: [], totalCount: 0 };
});
const server = (mcpServer as any).server;
@@ -519,7 +519,7 @@ describe.skip('MCP Telemetry Integration', () => {
}
expect(telemetry.trackToolUsage).toHaveBeenCalledWith(
'list_nodes',
'search_nodes',
true,
expect.any(Number)
);