n8n Pro MCP ⚙️

Full-instance management for self-hosted n8n — including queue mode — through the Model Context Protocol. 51 tools covering workflows, executions, tags, credentials, variables, projects, users, security audit, source control and health monitoring.

n8n-pro-mcp connects Claude Code, Claude Desktop, Cursor or any MCP client to your n8n instance via the official n8n public API v1, with automatic cursor pagination, exponential-backoff retry on reads (writes and webhook calls are never retried, so side effects can't duplicate), and offline workflow validation that catches the classic n8n mistakes (malformed {{ }} expressions, webhook data accessed without .body, Code nodes missing return [{json: {...}}]) before they reach your instance.

Why this one?

• Queue mode first-class — list_running_executions (live queue view), get_execution_stats (success rate + average duration per workflow) and check_health (healthz, readiness, API auth) were built for instances running EXECUTIONS_MODE=queue with workers and webhook processors. N8N_WEBHOOK_BASE_URL lets webhook calls target dedicated webhook processors.
• Complete API v1 coverage — tags, variables, projects, users, source control and cross-project transfers, beyond the usual workflow/execution CRUD.
• Offline validation built in — validate_workflow_json checks structure, connection integrity, orphan nodes, expression syntax, webhook .body access, Code node return format and hardcoded secrets without any API call. create_workflow/update_workflow run it automatically and refuse invalid payloads.
• Safe partial updates — update_workflow fetches the current workflow, merges only what you pass and strips read-only fields, so you never lose nodes by sending an incomplete PUT.
• Tags by name — set_workflow_tags accepts tag names and creates missing ones; no manual ID juggling.
• Ops compositions the raw API doesn't have — summarize_execution_error (just the failing node + error, not a giant JSON dump), prune_executions (bulk cleanup with dry run), wait_for_execution (poll until terminal), clone_workflow and set_workflows_active_by_tag (tag-based kill switch).

Installation

npm install -g n8n-pro-mcp     # or use npx, no install needed

From source:

git clone https://github.com/helbertparanhos/n8n-pro-mcp.git && cd n8n-pro-mcp
npm install
npm run build

When running from source, you can copy .env.example to .env in the project root — the server loads it from the package root, not the working directory. When installed via npx, set the variables through your MCP client config instead (the .env file is not read from the npx cache).

Configuration

Claude Code

claude mcp add n8n-pro --env N8N_API_URL=https://n8n.yourdomain.com --env N8N_API_KEY=your-key -- npx -y n8n-pro-mcp

Or in .claude/settings.json / .mcp.json:

{
  "mcpServers": {
    "n8n-pro": {
      "command": "npx",
      "args": ["-y", "n8n-pro-mcp"],
      "env": {
        "N8N_API_URL": "https://n8n.yourdomain.com",
        "N8N_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "n8n-pro": {
      "command": "npx",
      "args": ["-y", "n8n-pro-mcp"],
      "env": {
        "N8N_API_URL": "https://n8n.yourdomain.com",
        "N8N_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

Same JSON block in Cursor's MCP settings (.cursor/mcp.json).

Tools (51)

Workflows (12)

Executions (10)

Tags (6)

list_tags, create_tag, update_tag, delete_tag, get_workflow_tags, set_workflow_tags (by name, auto-creates missing tags).

Credentials (4)

create_credential, delete_credential, get_credential_schema, transfer_credential. Secrets are write-only — the n8n API never returns credential data.

Variables (4)

list_variables, create_variable, update_variable, delete_variable (licensed feature).

Projects (7)

list_projects, create_project, update_project, delete_project, plus member management: add_user_to_project, remove_user_from_project, change_user_project_role (licensed feature).

Users (5)

list_users, get_user, create_user (invite), delete_user, change_user_role.

System (3)

Queue mode playbook

With EXECUTIONS_MODE=queue (main + workers + Redis):

1. check_health — confirms the main process and DB are up.
2. list_running_executions — what is actually in flight right now; a growing list with old startedAt values means workers are starved or stuck.
3. get_execution_stats — which workflows fail or crawl; sorted worst-first by success rate.
4. run_webhook with N8N_WEBHOOK_BASE_URL pointing at your webhook processors to test the production ingestion path end to end.

Development