1. Conduid
  2. Automation
  3. tcs-n8n
MCP server · Automation

tcs-n8n

MCP server for n8n workflow automation. Manage workflows, executions, tags, variables, credentials and users via the Model Context Protocol.

Unclaimed automation
39Low

Scored 5 months ago · breakdown

About tcs-n8n

tcs-n8n is an MCP server published by git+ntatschner in the Automation category: mCP server for n8n workflow automation. Manage workflows, executions, tags, variables, credentials and users via the Model Context Protocol.

Install

Install
npx @thecodesaiyan/tcs-n8n-mcp
Claude Code
claude mcp add tcs-n8n-mcp -- npx -y @thecodesaiyan/tcs-n8n-mcp
npx
npx -y @thecodesaiyan/tcs-n8n-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (8)

activate_workflowActivate a workflow so it runs on its configured triggers

Parameters not published.

create_workflowCreate a new workflow with optional nodes and connections

Parameters not published.

deactivate_workflowDeactivate a workflow to stop trigger-based execution

Parameters not published.

delete_workflowPermanently delete a workflow

Parameters not published.

execute_workflowExecute a workflow immediately and return the execution ID

Parameters not published.

get_workflowGet full workflow details including nodes, connections, and settings

Parameters not published.

list_workflowsList all workflows with pagination

Parameters not published.

update_workflowUpdate an existing workflow's name, nodes, connections, or settings

Parameters not published.

Ask AI

✦

Ask AI about tcs-n8n

Powered by Claude · Grounded in docs

I know everything about tcs-n8n. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

4 checks have not been run yet.

README

@thecodesaiyan/tcs-n8n-mcp

Manage your n8n workflows through AI assistants

npm version Node.js MCP CI

An MCP server that gives AI assistants full control over your n8n workflow automation platform. List, create, update, execute, and manage workflows, executions, tags, variables, credentials, and users — all through natural language.

Installation · Tools · Security · Development


Features

  • 22 tools covering the full n8n REST API
  • Works everywhere — Claude Code, Claude Desktop, VS Code, Cursor, Windsurf, Cline
  • Secure by default — ID validation, sanitised errors, masked secrets, request timeouts
  • Flexible authentication — API key (default), Bearer token, or Basic Auth
  • Zero config — just provide your n8n API key and go
  • Lightweight — under 30KB, no runtime dependencies beyond the MCP SDK and Zod

Prerequisites


Installation

Quick Start

npx @thecodesaiyan/tcs-n8n-mcp --setup

The setup wizard walks you through configuration, tests your connection, and outputs ready-to-paste config for your MCP client.

Windows users: npx cannot resolve bin commands from scoped packages on Windows. Install globally instead:

npm install -g @thecodesaiyan/tcs-n8n-mcp
tcs-n8n-mcp --setup

Environment Variables

Variable Required Default Description
N8N_API_KEY Yes — Your n8n API key (or password for basic auth)
N8N_API_URL No http://localhost:5678 Base URL of your n8n instance
N8N_AUTH_TYPE No apikey Authentication method: apikey, bearer, or basic
N8N_API_USER Only for basic — Username for basic authentication
N8N_TIMEOUT_MS No 30000 Request timeout in milliseconds

Authentication Types

  • apikey (default) — Sends X-N8N-API-KEY header. This is n8n's standard API authentication.
  • bearer — Sends Authorization: Bearer <token> header.
  • basic — Sends Authorization: Basic <base64> header. Requires N8N_API_USER to be set.

Client Setup

Option A: Interactive wizard

npx @thecodesaiyan/tcs-n8n-mcp --setup

Option B: CLI command

macOS / Linux:

claude mcp add n8n -e N8N_API_URL=http://localhost:5678 -e N8N_API_KEY=your-api-key -- npx -y @thecodesaiyan/tcs-n8n-mcp

Windows (install globally first):

npm install -g @thecodesaiyan/tcs-n8n-mcp
claude mcp add n8n -e N8N_API_URL=http://localhost:5678 -e N8N_API_KEY=your-api-key -- tcs-n8n-mcp

Option C: Manual config

Add to ~/.claude.json:

macOS / Linux:

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": ["-y", "@thecodesaiyan/tcs-n8n-mcp"],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Windows:

{
  "mcpServers": {
    "n8n": {
      "command": "tcs-n8n-mcp",
      "args": [],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Add to your Claude Desktop config file:

OS Path
Windows %APPDATA%\Claude\claude_desktop_config.json
macOS ~/Library/Application Support/Claude/claude_desktop_config.json
Linux ~/.config/Claude/claude_desktop_config.json

macOS / Linux:

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": ["-y", "@thecodesaiyan/tcs-n8n-mcp"],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Windows (run npm install -g @thecodesaiyan/tcs-n8n-mcp first):

{
  "mcpServers": {
    "n8n": {
      "command": "tcs-n8n-mcp",
      "args": [],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Restart Claude Desktop after saving.

Add to .vscode/mcp.json in your project, or use Command Palette > MCP: Open User Configuration:

macOS / Linux:

{
  "servers": {
    "n8n": {
      "command": "npx",
      "args": ["-y", "@thecodesaiyan/tcs-n8n-mcp"],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Windows (run npm install -g @thecodesaiyan/tcs-n8n-mcp first):

{
  "servers": {
    "n8n": {
      "command": "tcs-n8n-mcp",
      "args": [],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-level):

macOS / Linux:

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": ["-y", "@thecodesaiyan/tcs-n8n-mcp"],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Windows (run npm install -g @thecodesaiyan/tcs-n8n-mcp first):

{
  "mcpServers": {
    "n8n": {
      "command": "tcs-n8n-mcp",
      "args": [],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Add to your Windsurf config file:

OS Path
Windows %USERPROFILE%\.codeium\windsurf\mcp_config.json
macOS / Linux ~/.codeium/windsurf/mcp_config.json

macOS / Linux:

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": ["-y", "@thecodesaiyan/tcs-n8n-mcp"],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Windows (run npm install -g @thecodesaiyan/tcs-n8n-mcp first):

{
  "mcpServers": {
    "n8n": {
      "command": "tcs-n8n-mcp",
      "args": [],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Open MCP Servers > Configure > Advanced MCP Settings and add:

macOS / Linux:

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": ["-y", "@thecodesaiyan/tcs-n8n-mcp"],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Windows (run npm install -g @thecodesaiyan/tcs-n8n-mcp first):

{
  "mcpServers": {
    "n8n": {
      "command": "tcs-n8n-mcp",
      "args": [],
      "env": {
        "N8N_API_KEY": "your-api-key-here",
        "N8N_API_URL": "http://localhost:5678"
      }
    }
  }
}

Available Tools (22)

Workflows (8)

Tool Description
list_workflows List all workflows with pagination
get_workflow Get full workflow details including nodes, connections, and settings
create_workflow Create a new workflow with optional nodes and connections
update_workflow Update an existing workflow's name, nodes, connections, or settings
delete_workflow Permanently delete a workflow
activate_workflow Activate a workflow so it runs on its configured triggers
deactivate_workflow Deactivate a workflow to stop trigger-based execution
execute_workflow Execute a workflow immediately and return the execution ID

Executions (3)

Tool Description
list_executions List executions with optional filters for workflow ID and status
get_execution Get full execution details including per-node results and errors
delete_execution Delete an execution record

Tags (4)

Tool Description
list_tags List all tags used for organising workflows
create_tag Create a new tag
update_tag Rename an existing tag
delete_tag Delete a tag

Variables (4)

Tool Description
list_variables List all environment variables (values are masked for security)
create_variable Create a new key-value environment variable
update_variable Update an existing variable's key or value
delete_variable Delete an environment variable

Credentials (1)

Tool Description
list_credentials List all credentials (metadata only — secrets are never exposed)

Users (2)

Tool Description
list_users List all users with their roles and status
get_user Get full details of a user by ID

Security

Protection Description
ID Validation All resource IDs are validated as numeric strings to prevent path traversal attacks
Error Sanitisation API error responses only return HTTP status codes, never raw response bodies
Secret Masking Variable values are hidden in list output to prevent accidental secret exposure
Request Timeout All API calls have a configurable timeout (default 30s) to prevent hanging connections
No Key Logging API keys are never logged, echoed, or included in tool output
Credential Safety The credentials tool only returns metadata — secrets are never exposed
Startup Validation Credentials and connectivity are verified on startup before accepting any requests
Header Injection Prevention Basic auth credentials are validated to reject control characters

Development

git clone https://github.com/ntatschner/tcs-n8n-mcp.git
cd tcs-n8n-mcp
npm install

Commands

Command Description
npm run build Compile TypeScript to build/
npm test Run test suite
npm run test:coverage Run tests with coverage report
npm start Start the MCP server

Running locally

# API key auth (default)
N8N_API_KEY=your-key N8N_API_URL=http://localhost:5678 npm start

# Bearer token auth
N8N_AUTH_TYPE=bearer N8N_API_KEY=your-token N8N_API_URL=http://localhost:5678 npm start

# Basic auth
N8N_AUTH_TYPE=basic N8N_API_USER=admin N8N_API_KEY=password N8N_API_URL=http://localhost:5678 npm start

Project Structure

src/
  index.ts              Entry point, fetch wrapper, server setup
  config.ts             Auth type parsing, header building, timeout, connection check
  types.ts              Shared types, interfaces, response helpers
  validation.ts         Zod schemas for input validation
  tools/
    workflows.ts        Workflow CRUD, activation, execution
    executions.ts       Execution listing and management
    tags.ts             Tag CRUD operations
    variables.ts        Environment variable management
    credentials.ts      Credential metadata listing
    users.ts            User listing and details

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feat/my-feature)
  3. Run tests (npm test)
  4. Commit your changes (git commit -m 'feat: add my feature')
  5. Push to the branch (git push origin feat/my-feature)
  6. Open a Pull Request

License

MIT — Made by @ntatschner

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About tcs-n8n

How do I install tcs-n8n?

Run npx @thecodesaiyan/tcs-n8n-mcp, then add the server to your MCP client's configuration.

Is tcs-n8n safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 1 of the 2 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is tcs-n8n still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.