Server data from the Official MCP Registry
Manage self-hosted n8n (incl. queue mode): workflows, executions, users, audit — 51 tools.
Manage self-hosted n8n (incl. queue mode): workflows, executions, users, audit — 51 tools.
The n8n Pro MCP server is well-structured with proper authentication via API keys, appropriate permissions scoped to n8n instance management, and clean code practices. No malicious patterns or critical vulnerabilities detected. Minor findings around logging and error handling do not significantly impact the security posture. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
5 files analyzed · 7 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: N8N_API_URL
Environment variable: N8N_API_KEY
Environment variable: N8N_WEBHOOK_BASE_URL
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-helbertparanhos-n8n-pro-mcp": {
"env": {
"N8N_API_KEY": "your-n8n-api-key-here",
"N8N_API_URL": "your-n8n-api-url-here",
"N8N_WEBHOOK_BASE_URL": "your-n8n-webhook-base-url-here"
},
"args": [
"-y",
"n8n-pro-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
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.
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.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.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.set_workflow_tags accepts tag names and creates missing ones; no manual ID juggling.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).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).
| Variable | Required | Description |
|---|---|---|
N8N_API_URL | ✅ | Base URL of your instance (e.g. https://n8n.yourdomain.com) — no /api/v1 suffix |
N8N_API_KEY | ✅ | API key from n8n → Settings → n8n API → Create API key |
N8N_WEBHOOK_BASE_URL | — | Separate base URL for webhook calls (queue mode with dedicated webhook processors) |
N8N_API_TIMEOUT_MS | — | Per-request timeout in ms (default 30000) |
N8N_MAX_RETRIES | — | Retries on 429/5xx/network errors — applied to GET requests only, never to writes or webhook calls (default 3, 0 disables) |
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"
}
}
}
}
~/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"
}
}
}
}
Same JSON block in Cursor's MCP settings (.cursor/mcp.json).
| Tool | Description |
|---|---|
list_workflows | List with filters (active, tags, project, name) + auto pagination |
get_workflow | Full JSON or lightweight summary of one workflow |
create_workflow | Create from JSON, with automatic offline validation |
update_workflow | Partial update — fetch, merge, validate, PUT |
delete_workflow | Permanently delete |
activate_workflow / deactivate_workflow | Toggle triggers |
transfer_workflow | Move between projects |
search_workflows | Free-text search across names, node names and node types |
clone_workflow | Duplicate a workflow as an inactive copy |
set_workflows_active_by_tag | Bulk activate/deactivate by tag, with dry run |
validate_workflow_json | Offline validation, no API call |
| Tool | Description |
|---|---|
list_executions | Filter by status/workflow/project, with durations |
get_execution | Summary or full node-level run data for debugging |
delete_execution | Remove an execution record |
retry_execution | Retry a failed/stopped execution |
list_running_executions | Queue-mode live view of running/queued executions |
run_webhook | Trigger workflows via production or test webhook |
wait_for_execution | Poll an execution until it reaches a terminal state |
summarize_execution_error | Failing node + error message only — no giant JSON dump |
prune_executions | Bulk-delete old execution records, dry run by default |
get_execution_stats | Success rate + avg duration per workflow over a sample |
list_tags, create_tag, update_tag, delete_tag, get_workflow_tags, set_workflow_tags (by name, auto-creates missing tags).
create_credential, delete_credential, get_credential_schema, transfer_credential. Secrets are write-only — the n8n API never returns credential data.
list_variables, create_variable, update_variable, delete_variable (licensed feature).
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).
list_users, get_user, create_user (invite), delete_user, change_user_role.
| Tool | Description |
|---|---|
check_health | healthz + readiness (DB) + API auth, with a plain-language summary |
generate_audit | n8n's built-in security audit (credentials, database, nodes, filesystem, instance) |
pull_source_control | Pull from the connected git repository |
With EXECUTIONS_MODE=queue (main + workers + Redis):
check_health — confirms the main process and DB are up.list_running_executions — what is actually in flight right now; a growing list with old startedAt values means workers are starved or stuck.get_execution_stats — which workflows fail or crawl; sorted worst-first by success rate.run_webhook with N8N_WEBHOOK_BASE_URL pointing at your webhook processors to test the production ingestion path end to end.npm test # build + unit tests (validation rules, client helpers, .env parser)
npm run watch # incremental compile
npm run inspector # interactive testing with @modelcontextprotocol/inspector
CI (GitHub Actions) runs build, tests and npm audit on every push and PR.
N8N_PUBLIC_API_DISABLED not set) and an API keyCreated by Helbert Paranhos at Strat Academy.
If this project helped you, consider starring ⭐ the repository and following Strat Academy for more AI automation tooling.
MIT © Helbert Paranhos / Strat Academy — see LICENSE.
Be the first to review this server!
by Modelcontextprotocol · Productivity
Knowledge graph-based persistent memory across sessions
by Modelcontextprotocol · Productivity
Time and timezone conversion capabilities for your AI assistant
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.