### Local Development Setup Commands

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/CONTRIBUTING.md

Commands to clone the repository, set up n8n docs, install dependencies, build the project, initialize the database, and start the server.

```bash
git clone https://github.com/czlonkowski/n8n-mcp.git
cd n8n-mcp

git clone https://github.com/n8n-io/n8n-docs.git ../n8n-docs

npm install
npm run build

npm run rebuild

npm start          # stdio mode for Claude Desktop
npm run start:http # HTTP mode for remote access
```

--------------------------------

### Test MCP tool for node essentials with includeExamples=true

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/P0-R3-TEST-PLAN.md

Example of using the MCP tool to get node essentials, including examples.

```javascript
get_node_essentials({nodeType: "nodes-base.webhook", includeExamples: true})
```

--------------------------------

### Local Development Setup for n8n-MCP

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/HTTP_DEPLOYMENT.md

For local development without Docker. This involves cloning the repository, installing dependencies, building the project, configuring environment variables, and starting the HTTP server.

```bash
# 1. Clone and setup
git clone https://github.com/czlonkowski/n8n-mcp.git
cd n8n-mcp
npm install
npm run build
npm run rebuild

# 2. Configure environment
export MCP_MODE=http
export AUTH_TOKEN=$(openssl rand -base64 32)
export PORT=3000

# 3. Start server
npm run start:http
```

--------------------------------

### Get Documentation for n8n-MCP Tools

Source: https://context7.com/czlonkowski/n8n-mcp/llms.txt

Call the `tools_documentation` tool to get quick-start guides or detailed reference documentation for specific n8n-MCP tools. Omit the `topic` argument for an overview, or specify a `topic` for targeted information. Use `depth='full'` for exhaustive details.

```json
{
  "name": "tools_documentation",
  "arguments": {
    "topic": "search_nodes",
    "depth": "full"
  }
}
```

--------------------------------

### Manual Local Setup for n8n-MCP

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/N8N_DEPLOYMENT.md

Configure and start n8n-MCP locally by setting environment variables for n8n integration, API URLs, and authentication tokens. Ensure n8n is running and an API key is available.

```bash
# Set environment variables
export N8N_MODE=true
export MCP_MODE=http                       # Required for HTTP mode
export N8N_API_URL=http://localhost:5678  # Your n8n instance URL
export N8N_API_KEY=your-api-key-here       # Your n8n API key
export WEBHOOK_SECURITY_MODE=moderate      # Required when N8N_API_URL is localhost or RFC1918
export MCP_AUTH_TOKEN=test-token-minimum-32-chars-long
export AUTH_TOKEN=test-token-minimum-32-chars-long  # Same value as MCP_AUTH_TOKEN
export PORT=3001

# Start the server
npm start
```

--------------------------------

### Test MCP tool with includeExamples=true

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/P0-R3-TEST-PLAN.md

Example of using the MCP tool to search nodes, including examples.

```javascript
search_nodes({query: "webhook", includeExamples: true})
```

--------------------------------

### Search n8n Nodes with Examples

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/README.md

Use this to find nodes matching a query and include example configurations. Set 'includeExamples' to true.

```javascript
search_nodes({query: 'keyword', includeExamples: true})
```

--------------------------------

### Get Node Essentials with Examples

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/P0_IMPLEMENTATION_PLAN.md

Tests the `getNodeEssentials` function to ensure it returns examples when requested. Verifies that the returned examples contain expected properties like 'url'.

```typescript
describe('Enhanced Tools with Examples', () => {
  it('get_node_essentials should return examples when requested', async () => {
    const result = await getNodeEssentials('n8n-nodes-base.httpRequest', {
      includeExamples: true
    });

    expect(result.examples).toBeDefined();
    expect(result.examples.length).toBeGreaterThan(0);
    expect(result.examples[0].config).toHaveProperty('url');
  });

  it('search_nodes should return examples when requested', async () => {
    const result = await searchNodes('webhook', { includeExamples: true });

    expect(result.length).toBeGreaterThan(0);
    expect(result[0].examples).toBeDefined();
  });

  it('get_node_for_task should not exist', async () => {
    expect(toolRegistry.has('get_node_for_task')).toBe(false);
  });
});
```

--------------------------------

### tools_documentation

Source: https://context7.com/czlonkowski/n8n-mcp/llms.txt

Get usage documentation for n8n-MCP tools. Returns a quick-start guide or per-tool reference documentation. Call without arguments for an overview, or supply `topic` to target a specific tool. Use `depth='full'` for exhaustive details.

```APIDOC
## tools_documentation

### Description
Get usage documentation for n8n-MCP tools. Returns a quick-start guide or per-tool reference documentation. Call without arguments for an overview, or supply `topic` to target a specific tool. Use `depth='full'` for exhaustive details.

### Method
MCP Tool Call

### Parameters
#### Arguments
- **topic** (string) - Optional - The specific tool to get documentation for. If omitted, an overview is returned.
- **depth** (string) - Optional - Specifies the level of detail for the documentation. Use 'full' for exhaustive details.

### Request Example
```json
{
  "name": "tools_documentation",
  "arguments": {
    "topic": "search_nodes",
    "depth": "full"
  }
}
```

### Response
#### Success Response
- **documentation** (string) - Markdown formatted documentation for the requested tool or an overview.
```

--------------------------------

### Explicit Parameter Configuration Example

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/ANTIGRAVITY_SETUP.md

Demonstrates the importance of explicitly setting all parameters, as relying on defaults can lead to runtime failures. The 'WORKS' example shows the correct explicit configuration.

```json
// ❌ FAILS at runtime
{
  "resource": "message",
  "operation": "post",
  "text": "Hello"
}

// ✅ WORKS - all parameters explicit
{
  "resource": "message",
  "operation": "post",
  "select": "channel",
  "channelId": "C123",
  "text": "Hello"
}
```

--------------------------------

### Example CHANGELOG Entry for get_node_for_task Removal

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/P0_IMPLEMENTATION_PLAN.md

Demonstrates how to document the removal of a tool and its replacement, including migration examples and benefits.

```markdown
## [2.15.0] - 2025-10-09

### BREAKING CHANGES
- **Removed:** `get_node_for_task` tool
  - **Replacement:** Use `search_nodes` with `includeExamples: true`
  - **Migration:** `get_node_for_task({task: "webhook"})` → `search_nodes({query: "webhook", includeExamples: true})`
  - **Benefit:** Access to 2,646 real templates vs 31 hardcoded tasks

```

--------------------------------

### Install and Build n8n-MCP Locally

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/README_CLAUDE_SETUP.md

Use these commands to clone the n8n-MCP repository, install dependencies, and build the project for local use. Ensure Node.js is installed.

```bash
git clone https://github.com/czlonkowski/n8n-mcp.git
cd n8n-mcp
npm install
npm run build
npm run rebuild
```

--------------------------------

### Tool Node with $fromAI Example

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/N8N_AI_WORKFLOW_BUILDER_ANALYSIS.md

Example demonstrating how to set parameters for a Tool node using values dynamically retrieved by $fromAI.

```typescript
{
  nodeId: "gmail-tool-789",
  changes: [
    "Set sendTo to {{ $fromAI('to') }}",
    "Set subject to {{ $fromAI('subject') }}",
    "Set message to {{ $fromAI('message_html') }}"
  ]
}
```

--------------------------------

### Get Standard Node Details

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/README.md

Retrieve essential node properties and examples. Set 'detail' to 'standard' and 'includeExamples' to true.

```javascript
get_node({nodeType, detail: 'standard', includeExamples: true})
```

--------------------------------

### Install Claude Skills via Marketplace (Method 2)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/CLAUDE_CODE_SETUP.md

Add the n8n-skills repository as a marketplace and then install the 'n8n-mcp-skills' plugin. This method allows browsing and selecting from available plugins.

```bash
# Add as marketplace, then browse and install
/plugin marketplace add czlonkowski/n8n-skills

# Then browse available plugins
/plugin install
# Select "n8n-mcp-skills" from the list
```

--------------------------------

### Systemd Service Setup Script

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/HTTP_DEPLOYMENT.md

Shell commands to set up the n8n-mcp systemd service on Linux. This includes creating users, directories, generating secure tokens, deploying the application, and starting the service.

```bash
# Create user and directories
sudo useradd -r -s /bin/false n8n-mcp
sudo mkdir -p /opt/n8n-mcp /etc/n8n-mcp
sudo chown n8n-mcp:n8n-mcp /opt/n8n-mcp

# Create secure token
sudo sh -c 'openssl rand -base64 32 > /etc/n8n-mcp/auth_token'
sudo chmod 600 /etc/n8n-mcp/auth_token
sudo chown n8n-mcp:n8n-mcp /etc/n8n-mcp/auth_token

# Deploy application
sudo -u n8n-mcp git clone https://github.com/czlonkowski/n8n-mcp.git /opt/n8n-mcp
cd /opt/n8n-mcp
sudo -u n8n-mcp npm install --production
sudo -u n8n-mcp npm run build
sudo -u n8n-mcp npm run rebuild

# Start service
sudo systemctl daemon-reload
sudo systemctl enable n8n-mcp
sudo systemctl start n8n-mcp

```

--------------------------------

### Print Webhook Setup Instructions

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/integration-testing-plan.md

Prints setup instructions for the required webhook workflows to the console. It iterates through webhook configurations and displays the method, name, path, and the corresponding .env variable name.

```typescript
export function printSetupInstructions(): void {
  console.log(`
╔════════════════════════════════════════════════════════════════╗
║  WEBHOOK WORKFLOW SETUP REQUIRED                               ║
╠════════════════════════════════════════════════════════════════╣
║                                                                ║
║  Integration tests require 4 pre-activated webhook workflows:  ║
║                                                                ║
║  1. Create workflows manually in n8n UI                        ║
║  2. Use the configurations shown below                         ║
║  3. ACTIVATE each workflow in n8n UI                           ║
║  4. Copy workflow IDs to .env file                             ║
║                                                                ║
╚════════════════════════════════════════════════════════════════╝

Required workflows:
`);

  Object.entries(WEBHOOK_WORKFLOW_CONFIGS).forEach(([method, config]) => {
    console.log(`
${method} Method:
  Name: ${config.name}
  Path: ${config.nodes[0].parameters.path}
  .env variable: N8N_TEST_WEBHOOK_${method}_ID
`);
  });
}

```

--------------------------------

### Enhance getNodeEssentials with Examples (TypeScript)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/P0_IMPLEMENTATION_PLAN.md

Updates the `getNodeEssentials` handler to optionally include real-world configuration examples from popular templates. Requires a database query to fetch example data.

```typescript
async function getNodeEssentials(
  nodeType: string,
  options?: { includeExamples?: boolean }): Promise<any> {
  const node = repository.getNode(nodeType);
  if (!node) {
    return {
      success: false,
      error: `Node type "${nodeType}" not found. Use search_nodes to find available nodes.`
    };
  }

  const result = {
    nodeType,
    displayName: node.displayName,
    description: node.description,
    category: node.category,
    // ... existing essentials fields ...
  };

  // NEW: Add real-world examples if requested
  if (options?.includeExamples) {
    const examples = db.prepare(`
      SELECT
        parameters_json,
        template_name,
        template_views,
        complexity,
        use_cases,
        has_credentials,
        has_expressions
      FROM template_node_configs
      WHERE node_type = ?
      ORDER BY rank
      LIMIT 3
    `).all(nodeType);

    result.examples = examples.map(ex => ({
      config: JSON.parse(ex.parameters_json),
      source: `${ex.template_name} (${(ex.template_views / 1000).toFixed(0)}k views)`,
      complexity: ex.complexity,
      useCases: JSON.parse(ex.use_cases).slice(0, 2),
      hasAuth: ex.has_credentials === 1,
      hasExpressions: ex.has_expressions === 1
    }));
  }

  return result;
}
```

--------------------------------

### Building Workflow from Scratch

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/ANTIGRAVITY_SETUP.md

Example of building a workflow from scratch, involving parallel discovery, configuration, and validation steps.

```javascript
// STEP 1: Discovery (parallel execution)
[Silent execution]
search_nodes({query: 'slack', includeExamples: true})
search_nodes({query: 'communication trigger'})

// STEP 2: Configuration (parallel execution)
[Silent execution]
get_node({nodeType: 'n8n-nodes-base.slack', detail: 'standard', includeExamples: true})
get_node({nodeType: 'n8n-nodes-base.webhook', detail: 'standard', includeExamples: true})

// STEP 3: Validation (parallel execution)
[Silent execution]
validate_node({nodeType: 'n8n-nodes-base.slack', config, mode: 'minimal'})
validate_node({nodeType: 'n8n-nodes-base.slack', config: fullConfig, mode: 'full', profile: 'runtime'})

// STEP 4: Build
// Construct workflow with validated configs
// ⚠️ Set ALL parameters explicitly

// STEP 5: Validate
[Silent execution]
validate_workflow(workflowJson)

// Response after all tools complete:
"Created workflow: Webhook → Slack
Validation: ✅ Passed"
```

--------------------------------

### Start Services with Docker Compose

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/N8N_HTTP_STREAMABLE_SETUP.md

Starts n8n and n8n-mcp services using docker-compose.yml. Ensure services are stopped and removed before starting to avoid conflicts.

```bash
# Stop any existing containers
docker stop n8n n8n-mcp && docker rm n8n n8n-mcp

# Start with HTTP Streamable configuration
docker-compose -f docker-compose.n8n.yml up -d

# Services will be available at:
# - n8n: http://localhost:5678
# - n8n-mcp: http://localhost:3000
```

--------------------------------

### Get Node Parameter Examples

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/N8N_AI_WORKFLOW_BUILDER_ANALYSIS.md

Demonstrates how to retrieve specific parameter values from a node using different path syntaxes. Useful when workflow JSON has been trimmed.

```typescript
{
  nodeId: "http-node-123",
  path: "url"
}
```

```typescript
{
  nodeId: "http-node-123",
  path: "headerParameters.parameters[0].value"
}
```

```typescript
{
  nodeId: "set-node-456",
  path: "options.includeOtherFields"
}
```

--------------------------------

### HTTP Request Node Configuration Example

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/N8N_AI_WORKFLOW_BUILDER_ANALYSIS.md

Example of how to configure an HTTP Request node using natural language instructions for URL, method, headers, and body.

```typescript
{
  nodeId: "http-node-123",
  changes: [
    "Set the URL to https://api.weather.com/v1/forecast",
    "Set method to POST",
    "Add header Content-Type with value application/json",
    "Set body to { city: {{ $json.city }} }"
  ]
}
```

--------------------------------

### Example: Add Slack Notification and Connection

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/workflow-diff-examples.md

This example demonstrates adding a Slack notification node and connecting it to an existing 'Process Data' node.

```json
{
  "id": "workflow-123",
  "operations": [
    {
      "type": "addNode",
      "node": {
        "name": "Send Slack Alert",
        "type": "n8n-nodes-base.slack",
        "position": [1000, 300],
        "parameters": {
          "resource": "message",
          "operation": "post",
          "channel": "#alerts",
          "text": "Workflow completed successfully!"
        }
      }
    },
    {
      "type": "addConnection",
      "source": "Process Data",
      "target": "Send Slack Alert"
    }
  ]
}
```

--------------------------------

### Enable and Start Systemd Service

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/HTTP_DEPLOYMENT.md

Commands to enable the n8n-mcp service to start on boot and to manually start it.

```bash
sudo systemctl enable n8n-mcp
sudo systemctl start n8n-mcp

```

--------------------------------

### Set Node Configuration Example

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/N8N_AI_WORKFLOW_BUILDER_ANALYSIS.md

Example of configuring a Set node by adding or modifying fields with static values or data from previous nodes.

```typescript
{
  nodeId: "set-node-456",
  changes: [
    "Add field 'status' with value 'processed'",
    "Add field 'timestamp' with current date",
    "Add field 'userId' from previous HTTP Request node"
  ]
}
```

--------------------------------

### Starting Docker Services

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/N8N_DEPLOYMENT.md

Command to start the n8n-MCP and Caddy services defined in your docker-compose.yml file. Ensure you have created the Caddyfile and .env file beforehand.

```bash
docker compose up -d
```

--------------------------------

### Manual Installation of Claude Skills (Method 3)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/CLAUDE_CODE_SETUP.md

Manually install n8n-skills by cloning the repository, copying the skills to your Claude Code skills directory, and then reloading Claude Code.

```bash
# 1. Clone the repository
git clone https://github.com/czlonkowski/n8n-skills.git

# 2. Copy skills to your Claude Code skills directory
cp -r n8n-skills/skills/* ~/.claude/skills/

# 3. Reload Claude Code
# Skills will activate automatically
```

--------------------------------

### Install Claude Skills Plugin (Method 1)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/CLAUDE_CODE_SETUP.md

Install the n8n-skills plugin directly using the provided command. This is the recommended method for adding specialized skills to Claude Code.

```bash
/plugin install czlonkowski/n8n-skills
```

--------------------------------

### Install Node.js and npx

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/HTTP_DEPLOYMENT.md

If 'npx' command is not found, install Node.js version 18 or later, which includes npx. Alternatively, find the npx location and use its full path.

```bash
# Install Node.js 18+ which includes npx
# Or use full path:
which npx  # Find npx location
# Use that path in Claude config
```

--------------------------------

### Run MCP Server Commands

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/CLAUDE.md

Commands to start the MCP server in different modes. Use 'npm start' for stdio mode and 'npm run start:http' for HTTP mode. 'npm run dev' rebuilds the database and validates, while 'npm run dev:http' runs the HTTP server with auto-reload.

```bash
# Running the Server
npm start              # Start MCP server in stdio mode
npm run start:http     # Start MCP server in HTTP mode
npm run dev            # Build, rebuild database, and validate
npm run dev:http       # Run HTTP server with auto-reload
```

--------------------------------

### Enhance get_node_essentials with Examples

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/P0_IMPLEMENTATION_PLAN.md

Updates the `getNodeEssentials` function to optionally include real-world examples from popular templates. The tool definition is also updated to reflect the new `includeExamples` option.

```APIDOC
## Function: getNodeEssentials

### Description
Retrieves essential information about a specific n8n node type, with an option to include real-world configuration examples.

### Parameters
#### Optional Parameters
- **includeExamples** (boolean) - Optional - If true, includes 2-3 real configuration examples from popular templates. Defaults to false.

### Request Example
```json
{
  "nodeType": "n8n-nodes-base.httpRequest"
}
```

### Response
#### Success Response
- **nodeType** (string) - The type of the node.
- **displayName** (string) - The display name of the node.
- **description** (string) - The description of the node.
- **category** (string) - The category the node belongs to.
- **examples** (array) - An array of example configurations if `includeExamples` is true.
  - **config** (object) - The configuration of the example.
  - **source** (string) - The source template name and views.
  - **complexity** (number) - The complexity of the example.
  - **useCases** (array) - An array of use cases for the example.
  - **hasAuth** (boolean) - Indicates if the example requires authentication.
  - **hasExpressions** (boolean) - Indicates if the example uses expressions.

#### Response Example (with includeExamples: true)
```json
{
  "nodeType": "n8n-nodes-base.httpRequest",
  "displayName": "HTTP Request",
  "description": "Make requests to any HTTP(S) endpoint.",
  "category": "network",
  "examples": [
    {
      "config": {
        "url": "https://example.com"
      },
      "source": "Example GET Request (100k views)",
      "complexity": 1,
      "useCases": ["Making GET requests"],
      "hasAuth": false,
      "hasExpressions": false
    }
  ]
}
```
```

--------------------------------

### n8n Message Post - Working Example (Explicit Parameters)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/README.md

This configuration works because all necessary parameters, such as 'select' and 'channelId', are explicitly provided.

```json
{
  "resource": "message",
  "operation": "post",
  "select": "channel",
  "channelId": "C123",
  "text": "Hello"
}
```

--------------------------------

### Basic Test Setup with Database Utilities

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/tests/utils/README.md

Demonstrates setting up an in-memory test database, seeding nodes, and performing a basic assertion. Ensure to cleanup the database after each test.

```typescript
import { createTestDatabase, seedTestNodes, dbHelpers } from '../utils/database-utils';

describe('My Test', () => {
  let testDb;
  
  afterEach(async () => {
    if (testDb) await testDb.cleanup();
  });
  
  it('should test something', async () => {
    // Create in-memory database
    testDb = await createTestDatabase();
    
    // Seed test data
    await seedTestNodes(testDb.nodeRepository);
    
    // Run your tests
    const node = testDb.nodeRepository.getNode('nodes-base.httpRequest');
    expect(node).toBeDefined();
  });
});
```

--------------------------------

### Copying Example Environment File

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/tests/setup/TEST_ENV_DOCUMENTATION.md

Use this command to create a `.env.test` file from a template if you encounter 'Missing required test environment variables' errors.

```bash
cp .env.test.example .env.test
```

--------------------------------

### Get Full Node Details

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/ANTIGRAVITY_SETUP.md

Retrieve comprehensive information about a node, including essential properties and examples. This is the default detail level.

```javascript
get_node({nodeType, detail: 'full', includeExamples: true})
```

--------------------------------

### Run n8n-MCP with npx

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/SELF_HOSTING.md

Execute n8n-MCP directly using npx without any prior installation. This is suitable for quick local testing or setup.

```bash
npx n8n-mcp
```

--------------------------------

### HTTP Request Node - Simple URL Fetch

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/TEMPLATE_MINING_ANALYSIS.md

Example configuration for an HTTP Request node making a simple GET request to a specified URL.

```json
{
  "url": "https://api.example.com/data",
  "options": {}
}
```

--------------------------------

### Mock n8n API Error Scenario

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/tests/mocks/README.md

Mock an error response for a GET request to a workflow endpoint. This example returns a 404 status with a JSON error message.

```typescript
useHandlers(
  http.get('*/api/v1/workflows/:id', () => {
    return HttpResponse.json(
      { message: 'Not found', code: 'NOT_FOUND' },
      { status: 404 }
    );
  })
);
```

--------------------------------

### Mock n8n API Success Scenario

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/tests/mocks/README.md

Mock a successful GET request for a specific workflow by ID. This example uses `workflowFactory` to generate dynamic mock data.

```typescript
useHandlers(
  http.get('*/api/v1/workflows/:id', ({ params }) => {
    return HttpResponse.json({
      data: workflowFactory.custom({ id: params.id as string })
    });
  })
);
```

--------------------------------

### Display Help for Fetch Command

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/MEMORY_TEMPLATE_UPDATE.md

View all available options and usage instructions for the fetch command.

```bash
npm run fetch:templates -- --help
```

--------------------------------

### Environment File Setup (.env)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/N8N_DEPLOYMENT.md

Sets up essential environment variables for n8n-MCP, including n8n API details and authentication tokens. Ensure to generate a strong random token for MCP_AUTH_TOKEN and AUTH_TOKEN.

```bash
AUTH_TOKEN=$(openssl rand -hex 32)
cat > .env << EOF
N8N_API_URL=https://your-n8n-instance.com
N8N_API_KEY=your-n8n-api-key-here
MCP_AUTH_TOKEN=$AUTH_TOKEN
AUTH_TOKEN=$AUTH_TOKEN
EOF
```

--------------------------------

### AI Agent Prompt for Workflow Creation

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/N8N_DEPLOYMENT.md

Example prompt for an AI Agent node to utilize MCP tools for n8n workflow creation. It outlines the steps for searching nodes, getting details, validating, and creating workflows.

```text
You are an n8n workflow expert. Use the MCP tools to:
1. Search for appropriate nodes using search_nodes
2. Get configuration details with get_node_essentials
3. Validate configurations with validate_workflow
4. Create the workflow if all validations pass
```

--------------------------------

### Development Commands

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/CONTRIBUTING.md

Common commands for building, testing, updating dependencies, and running the server in development mode.

```bash
# Build & Test
npm run build          # Build TypeScript
npm run rebuild        # Rebuild node database
npm run test-nodes     # Test critical nodes
npm run validate       # Validate node data
npm test               # Run all tests

# Update Dependencies
npm run update:n8n:check  # Check for n8n updates
npm run update:n8n        # Update n8n packages

# Run Server
npm run dev            # Development with auto-reload
npm run dev:http       # HTTP dev mode
```

--------------------------------

### Enhance searchNodes with Examples (TypeScript)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/P0_IMPLEMENTATION_PLAN.md

Modifies the `searchNodes` handler to optionally include example configurations for each found node. This enhances search results with practical usage examples.

```typescript
async function searchNodes(
  query: string,
  options?: {
    limit?: number;
    includeExamples?: boolean;
  }): Promise<any> {
  const nodes = repository.searchNodes(query, 'OR', options?.limit || 20);

  const results = nodes.map(node => {
    const result = {
      nodeType: node.nodeType,
      displayName: node.displayName,
      description: node.description,
      category: node.category
    };

    // NEW: Add examples if requested
    if (options?.includeExamples) {
      const examples = db.prepare(`
        SELECT parameters_json, template_name, complexity
        FROM template_node_configs
        WHERE node_type = ?
        ORDER BY rank
        LIMIT 2
      `).all(node.nodeType);

      result.examples = examples.map(ex => ({
        config: JSON.parse(ex.parameters_json),
        source: ex.template_name,
        complexity: ex.complexity
      }));
    }

    return result;
  });

  return results;
}
```

--------------------------------

### Build and Run n8n-MCP from Source (Cloud Docker)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/N8N_DEPLOYMENT.md

This is an alternative for cloud deployments if you need to build from source. It involves cloning the repository, building a local Docker image on the cloud server, and then running it. The environment variables should be configured similarly to other Docker deployments.

```bash
# Clone and build
git clone https://github.com/czlonkowski/n8n-mcp.git
cd n8n-mcp
docker build -t n8n-mcp:latest .

# Run using local image
docker run -d \
  --name n8n-mcp \
  -p 3000:3000 \
  # ... same environment variables as above
  n8n-mcp:latest
```

--------------------------------

### Run Prepared Release Script

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/AUTOMATED_RELEASES.md

Use this script for a guided release process. It prompts for the new version, updates relevant files, runs tests and builds, and prepares for a git commit.

```bash
npm run prepare:release
```

--------------------------------

### Load Test Environment in Setup Files

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/tests/setup/TEST_ENV_DOCUMENTATION.md

Call loadTestEnvironment early in your setup files to initialize the test environment configuration.

```typescript
import { loadTestEnvironment } from './test-env';

// Load test environment at the start of your setup
loadTestEnvironment();
```

--------------------------------

### Strategy Pattern: Build System Prompt

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/N8N_AI_WORKFLOW_BUILDER_ANALYSIS.md

Selects node-specific examples to append to the core instructions based on the node type. This allows for dynamic prompt generation tailored to different node functionalities.

```typescript
buildSystemPrompt(context) {
  let prompt = CORE_INSTRUCTIONS;

  if (isSetNode) prompt += SET_NODE_EXAMPLES;
  else if (isIfNode) prompt += IF_NODE_EXAMPLES;
  else if (isToolNode) prompt += TOOL_NODE_EXAMPLES;

  return prompt;
}
```

--------------------------------

### Full Template Rebuild

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/MEMORY_TEMPLATE_UPDATE.md

Execute this command to rebuild the entire database from scratch. This is recommended only for initial setup or if database corruption is suspected.

```bash
# Rebuild entire database from scratch (30-40 minutes)
npm run fetch:templates
```

--------------------------------

### Update .env.example for Integration Testing

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/integration-testing-plan.md

Configure environment variables for n8n API access, webhook URLs, and test-specific settings. Ensure these are set up correctly for the testing environment.

```bash
# ========================================
# INTEGRATION TESTING CONFIGURATION
# ========================================

# n8n API Configuration for Integration Tests
N8N_API_URL=http://localhost:5678
N8N_API_KEY=your-api-key-here

# Pre-activated Webhook URLs for Testing
# Create these workflows manually in n8n and activate them
# Store the full webhook URLs (not workflow IDs)
N8N_TEST_WEBHOOK_GET_URL=https://n8n-test.n8n-mcp.com/webhook/mcp-test-get
N8N_TEST_WEBHOOK_POST_URL=https://n8n-test.n8n-mcp.com/webhook/mcp-test-post
N8N_TEST_WEBHOOK_PUT_URL=https://n8n-test.n8n-mcp.com/webhook/mcp-test-put
N8N_TEST_WEBHOOK_DELETE_URL=https://n8n-test.n8n-mcp.com/webhook/mcp-test-delete

# Test Configuration
N8N_TEST_CLEANUP_ENABLED=true           # Enable automatic cleanup
N8N_TEST_TAG=mcp-integration-test       # Tag for test workflows
N8N_TEST_NAME_PREFIX=[MCP-TEST]         # Name prefix for test workflows

```

--------------------------------

### AI-Generated Metadata Example

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/TEMPLATE_MINING_ANALYSIS.md

Example of structured metadata generated by AI for a template, including categories, use cases, complexity, and required services.

```json
{
  "categories": ["automation", "integration", "data processing"],
  "complexity": "medium",
  "use_cases": [
    "Extract transaction data from Gmail",
    "Automate bookkeeping",
    "Expense tracking"
  ],
  "estimated_setup_minutes": 30,
  "required_services": ["Gmail", "Google Sheets", "Google Gemini"],
  "key_features": [
    "Fetch emails by label",
    "Extract transaction data",
    "Use LLM for structured output"
  ],
  "target_audience": ["Accountants", "Small business owners"]
}
```

--------------------------------

### Execute Unit Tests

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/P0-R3-TEST-PLAN.md

Run the new unit tests for fetch-templates-extraction, search-nodes-examples, and get-node-essentials-examples. All tests are expected to pass.

```bash
# Run new unit tests
npm test tests/unit/scripts/fetch-templates-extraction.test.ts
npm test tests/unit/mcp/search-nodes-examples.test.ts
npm test tests/unit/mcp/get-node-essentials-examples.test.ts

# Expected: All pass, 52 tests
```

--------------------------------

### Build and Run n8n-MCP from Source (Docker)

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/N8N_DEPLOYMENT.md

For advanced users needing custom modifications or contributing to development, this process involves cloning the repository, building a local Docker image, and then running the container using the locally built image. Replace placeholder environment variables as needed.

```bash
git clone https://github.com/czlonkowski/n8n-mcp.git
cd n8n-mcp

# Build Docker image
docker build -t n8n-mcp:latest .

# Run using your local image
docker run -d \
  --name n8n-mcp \
  -p 3000:3000 \
  -e N8N_MODE=true \
  -e MCP_MODE=http \
  -e MCP_AUTH_TOKEN=$(openssl rand -hex 32) \
  -e AUTH_TOKEN=$(openssl rand -hex 32) \
  # ... other settings
  n8n-mcp:latest
```

--------------------------------

### Example: Update Multiple Webhook Paths and Workflow Name

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/workflow-diff-examples.md

This example shows how to update the paths of multiple webhook nodes and rename the workflow simultaneously.

```json
{
  "id": "workflow-456",
  "operations": [
    {
      "type": "updateNode",
      "nodeName": "Webhook 1",
      "changes": {
        "parameters.path": "v2/webhook1"
      }
    },
    {
      "type": "updateNode",
      "nodeName": "Webhook 2",
      "changes": {
        "parameters.path": "v2/webhook2"
      }
    },
    {
      "type": "updateName",
      "name": "API v2 Webhooks"
    }
  ]
}
```

--------------------------------

### Webhook Workflow Configuration for GET Method

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/integration-testing-plan.md

Configuration for a webhook workflow designed for GET method testing. Requires manual activation in n8n UI.

```typescript
/**
 * Guide for setting up webhook workflows manually in n8n
 *
 * These workflows must be created manually and activated because
 * n8n API doesn't support workflow activation.
 *
 * For each HTTP method, create a workflow with:
 * 1. Single Webhook node
 * 2. Configured for the specific HTTP method
 * 3. Unique webhook path
 * 4. Activated in n8n UI
 * 5. Workflow ID added to .env
 */

export const WEBHOOK_WORKFLOW_CONFIGS = {
  GET: {
    name: '[MCP-TEST] Webhook GET',
    description: 'Pre-activated webhook for GET method testing',
    nodes: [
      {
        name: 'Webhook',
        type: 'n8n-nodes-base.webhook',
        typeVersion: 2,
        parameters: {
          httpMethod: 'GET',
          path: 'mcp-test-get',
          responseMode: 'lastNode'
        }
      }
    ]
  },
  POST: {
```

--------------------------------

### Local Test and Build Command

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/AUTOMATED_RELEASES.md

Before releasing, test your changes locally and build the project using these commands.

```bash
npm test && npm run build
```

--------------------------------

### List and Get n8n-MCP Server Status

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/CLAUDE_CODE_SETUP.md

Check the status of your n8n-MCP servers using the `list` command or get detailed information about a specific server like `n8n-mcp`.

```bash
claude mcp list
```

```bash
claude mcp get n8n-mcp
```

--------------------------------

### Rebuild Project and Database

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/README_CLAUDE_SETUP.md

Run this command to rebuild the project and ensure the database is set up correctly. This can resolve issues where the server appears but tools do not function.

```bash
npm run rebuild
```

--------------------------------

### Configuring Custom Database Path

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/DOCKER_TROUBLESHOOTING.md

Demonstrates the correct format for the NODE_DB_PATH environment variable, ensuring it ends with '.db'. Incorrect paths will be rejected.

```bash
# Correct
NODE_DB_PATH=/app/data/custom/my-nodes.db

# Incorrect (will be rejected)
NODE_DB_PATH=/app/data/custom/my-nodes
```

--------------------------------

### Enhance search_nodes with Examples

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/P0_IMPLEMENTATION_PLAN.md

Updates the `searchNodes` function to optionally include real-world examples for each found node. The tool definition is also updated to reflect the new `includeExamples` option.

```APIDOC
## Function: searchNodes

### Description
Searches for n8n nodes by a given query string. Optionally includes real-world configuration examples for each matching node.

### Parameters
#### Parameters
- **query** (string) - Required - The search query string.
- **limit** (number) - Optional - The maximum number of nodes to return. Defaults to 20.
- **includeExamples** (boolean) - Optional - If true, includes 2 real configuration examples per node. Defaults to false.

### Request Example
```json
{
  "query": "http",
  "limit": 10,
  "includeExamples": true
}
```

### Response
#### Success Response
- **nodeType** (string) - The type of the node.
- **displayName** (string) - The display name of the node.
- **description** (string) - The description of the node.
- **category** (string) - The category the node belongs to.
- **examples** (array) - An array of example configurations if `includeExamples` is true.
  - **config** (object) - The configuration of the example.
  - **source** (string) - The source template name.
  - **complexity** (number) - The complexity of the example.

#### Response Example (with includeExamples: true)
```json
[
  {
    "nodeType": "n8n-nodes-base.httpRequest",
    "displayName": "HTTP Request",
    "description": "Make requests to any HTTP(S) endpoint.",
    "category": "network",
    "examples": [
      {
        "config": {
          "url": "https://example.com"
        },
        "source": "Example GET Request",
        "complexity": 1
      }
    ]
  }
]
```
```

--------------------------------

### Execute Integration Tests

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/P0-R3-TEST-PLAN.md

Run the new integration tests for template-node-configs and template-examples-e2e. All tests are expected to pass.

```bash
# Run new integration tests
npm test tests/integration/database/template-node-configs.test.ts
npm test tests/integration/mcp/template-examples-e2e.test.ts

# Expected: All pass, 33 tests
```

--------------------------------

### Local Testing: Prepare NPM Package

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/AUTOMATED_RELEASES.md

Execute the command to prepare the NPM package for publishing, ensuring it's optimized and ready.

```bash
npm run prepare:publish
```

--------------------------------

### Example n8n Workflow JSON

Source: https://github.com/czlonkowski/n8n-mcp/blob/main/docs/local/N8N_AI_WORKFLOW_BUILDER_ANALYSIS.md

A concrete example of an n8n workflow represented in JSON format. This demonstrates the structure for defining nodes, their properties, and the connections between them, such as a schedule trigger connected to an HTTP request node.

```json
{
  "name": "Weather Workflow",
  "nodes": [
    {
      "id": "abc-123",
      "name": "Schedule Trigger",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1,
      "position": [240, 300],
      "parameters": {
        "rule": {
          "interval": [{ "field": "hours", "hoursInterval": 1 }]
        }
      }
    },
    {
      "id": "def-456",
      "name": "HTTP Request",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [480, 300],
      "parameters": {
        "method": "GET",
        "url": "https://api.weather.com/forecast"
      }
    }
  ],
  "connections": {
    "Schedule Trigger": {
      "main": [[
        {
          "node": "HTTP Request",
          "type": "main",
          "index": 0
        }
      ]]
    }
  }
}
```

--------------------------------

### Deploy n8n.io Template to Live Instance

Source: https://context7.com/czlonkowski/n8n-mcp/llms.txt

Downloads a template from the n8n template library and deploys it to a live instance. It can automatically upgrade versions, apply fixes for expression format and `typeVersion` issues, and strip credentials.

```json
{
  "name": "n8n_deploy_template",
  "arguments": {
    "templateId": 1234,
    "name": "My Chatbot Workflow",
    "autoUpgradeVersions": true,
    "autoFix": true,
    "stripCredentials": true
  }
}

// Response:
// {
//   "workflowId": "99",
//   "name": "My Chatbot Workflow",
//   "fixesApplied": 2,
//   "requiredCredentials": ["openAiApi", "slackOAuth2Api"],
//   "message": "Template deployed successfully. Configure credentials in n8n UI."
// }
```