n8n-manager-mcp
The n8n-manager-mcp server provides comprehensive management of n8n workflow automation instances via AI assistants, offering full control over workflows, executions, and server connections.
Workflow Management
List workflows – Retrieve all workflows with names, IDs, active status, and node counts
Get workflow details – Fetch complete workflow info including nodes, connections, and settings
Create workflows – Build new workflows by defining nodes, connections, and optionally activating immediately
Update workflows – Modify existing workflows by submitting updated workflow JSON
Delete workflows – Permanently remove a workflow from a server
Activate/Deactivate workflows – Toggle a workflow's active state
Execution Monitoring
List executions – View recent execution history with status (success/error/waiting), timing, and error details; filterable by workflow or status
Workflow Portability
Export workflows – Download a complete workflow as JSON for backup or migration
Import workflows – Upload workflow JSON to any connected n8n server, with optional auto-activation
Server Management
Add/update servers – Register n8n server connections with a name, URL, and API key
List servers – View all configured server connections
Ping server – Test connectivity to a configured server
Remove server – Delete a server from the configuration
Supports multi-server setups with a configurable default server for transferring workflows between instances
Node Discovery
Describe nodes – Browse available n8n node types by category (trigger, action, logic, transform, AI, or all) to assist in building workflows
Provides tools for managing n8n workflows, including listing, creating, updating, deleting, activating/deactivating workflows, viewing execution history, exporting/importing workflows, and browsing node types.
n8n Manager MCP Server
Part of the ellmos-ai family and open-bricks umbrella.
For AI Assistants & LLMs: An llms.txt index file is available in the root directory for fast context ingestion, tool catalog references, and directory listings.
MCP (Model Context Protocol) server for managing n8n workflows via AI assistants like Claude, Cursor, and Windsurf.
System Architecture
graph TD
A["AI Client (Claude / Cursor / Windsurf)"] -->|MCP Stdio Protocol| B["n8n Manager MCP Server"]
subgraph "n8n Manager MCP Server"
B --> C["Tool Router (19 Tools)"]
C --> D["Safety Layer (Read-Only / Backups / Audit)"]
C --> E["Multi-Server Manager"]
end
E -->|REST API (API Key / Basic Auth)| F["n8n Instance 1 (Local)"]
E -->|REST API (API Key / Basic Auth)| G["n8n Instance 2 (Cloud / Remote)"]
D --> H[("Local Store (~/.n8n-manager-mcp/)")]Related MCP server: n8n-MCP
Directory Status
npm package: published as
n8n-manager-mcpGlama listing: public directory page for the ellmos-ai repo
Enterprise DNA directory: additional public directory entry for
ellmos-ai/n8n-manager-mcpPulseMCP listing: indexed as
ellmos-ai-n8n-managerMCP namespace status: this repo contains
server.jsonandmcpNamemetadata forio.github.ellmos-ai/n8n-manager-mcp; some ecosystem directories still expose the legacyio.github.lukisch/n8n-manager-mcpname until their indexes refresh.Search context: best matched by
n8n MCP server,n8n workflow management MCP,AI assistant n8n workflows, andellmos-ai n8n-manager-mcp.
Features
19 Tools for complete n8n workflow management
List, create, update, delete, and activate/deactivate workflows
Safety controls: read-only mode, backup-before-delete/update, local restore, and audit log
Multi-server support (connect to multiple n8n instances)
Export/Import workflows between servers
View execution history and status
Built-in node catalog with descriptions
Zero dependencies on Python -- connects directly to n8n REST API
Installation
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"n8n-manager": {
"command": "npx",
"args": ["-y", "n8n-manager-mcp"]
}
}
}Claude Code
claude mcp add --scope user n8n-manager npx -y n8n-manager-mcpManual
npm install -g n8n-manager-mcpQuick Start
After installation, use these commands in your AI assistant:
Add your n8n server:
"Add my n8n server at http://localhost:5678 with API key abc123"
List workflows:
"Show me all workflows on my n8n server"
Create a workflow:
"Create an n8n workflow that triggers on a webhook, fetches data from an API, and sends a Slack message"
Check executions:
"Show me the last 10 workflow executions"
Available Tools
Tool | Description |
| List all workflows on a server |
| Get workflow details (nodes, connections) |
| Create a new workflow from nodes + connections |
| Update an existing workflow |
| Delete a workflow |
| Activate or deactivate a workflow |
| List recent executions with status |
| Export workflow as importable JSON |
| Import workflow JSON onto a server |
| Show local safety settings, backup directory, and audit log path |
| Toggle read-only mode, backup-before-mutation, and audit logging |
| List local workflow backups created before mutations |
| Restore a workflow from a local backup |
| Add/update n8n server connection |
| List configured servers |
| Test server connection |
| Remove a server |
| Browse available n8n node types |
| Read version history, recorded decisions, and sync history from an optional n8n-workflow-manager (opt-in, read-only) |
Optional: n8n-workflow-manager seam
n8n itself keeps no record of why a workflow changed. The sibling project
n8n-workflow-manager does: it
stores versions, a mandatory decision per mutation, and a sync history in a local
database. n8n_manager_history makes that record readable from this MCP server.
The seam is opt-in and read-only:
Without
N8N_MCP_MANAGER_URL, nothing changes — every tool talks to n8n directly, as before.With it set (for example
http://127.0.0.1:8100),n8n_manager_historyreads from the running manager. Omitworkflow_idto list the manager's workflows, pass it for full history.IDs are manager IDs, not n8n instance IDs. The manager stores that mapping but exposes no route to resolve it, so this server does not guess a translation.
If the manager is configured but unreachable, the tool fails with an explicit message instead of quietly answering from the n8n instance — that store has no decision history, so a substituted answer would be a different answer.
n8n_safety_statusreports the measured state of the seam (configured, reachable, manager version), not just the environment variable.
Setup: pip install n8n-workflow-manager, then n8n-manager serve (binds 127.0.0.1:8100).
The manager API is unauthenticated and loopback-only by design; a non-loopback URL is
flagged in n8n_safety_status.
Configuration
Server connections and safety settings are stored in ~/.n8n-manager-mcp/servers.json.
Safety defaults:
backup_before_mutations: truesaves workflow JSON before update, delete, activate/deactivate, and overwrite-restore operations.audit_log: trueappends mutation outcomes to~/.n8n-manager-mcp/audit.log.read_only: falsecan be enabled withn8n_set_safety_modeorN8N_MANAGER_READ_ONLY=1. The environment flag is an enforcement ceiling: while it is enabled, persisted settings andn8n_set_safety_modecannot turn read-only mode off.Backups are stored under
~/.n8n-manager-mcp/backups/and can be listed/restored with the backup tools. Server/workflow names are reduced to safe single path segments; reserved names, separators, traversal, and symlink/reparse escapes cannot leave that root, and listing exposes only regular.jsonbackups.n8n_add_servervalidates server connection input before saving: URLs must behttporhttpsbase URLs without embedded credentials, query strings, or fragments, and API keys must not contain whitespace.n8n_add_serverdefault semantics are explicit: the first server becomes default; an update withoutis_defaultpreserves the existing flag;truepromotes the server;falseintentionally removes its flag, after which default lookup falls back to the first configured server.
Development
npm install
npm run build # One-time build
npm run dev # Watch mode
npm start # Start server
npm test # Run test suite (vitest)
npm run smoke # Start the built MCP server and verify tool discoveryTesting
The test suite covers URL building, server input validation, server management, safety settings, backup path handling, workflow JSON construction, export/import validation, i18n language packs, repository hygiene, and error handling. The manager seam is tested against a local stub HTTP server, including its refusal to fall back to a direct n8n query.
npm test # Run all tests
npx vitest run # Same as above
npx vitest --watch # Watch mode
npm run smoke # Manual stdio MCP smoke test (requires npm run build first)Tests are verified on Windows, macOS, and Linux.
GitHub Actions additionally runs build, test, and npm package checks on Node.js 20, 22, and 24.
The smoke runner starts dist/index.js through the MCP SDK client, verifies all 19 tool registrations, and calls the safe n8n_describe_nodes catalog tool without requiring n8n credentials.
Related
n8n-workflow-manager — the state & history layer for humans (Web UI + REST API, Python): per-workflow change history and decision log, visual graph viewer, multi-server sync. Designed as a pair with this MCP server — the MCP is the AI action layer (create/update/delete/activate), the manager is where you review, document, and roll back. Memory & context (roadmap): an MCP server alone can't guarantee an agent checks prior context before a destructive change — that enforcement belongs in the manager (client-agnostic), with conversational context optionally from a pull-based history index like ctx (Apache-2.0). Planned: a shared history/decision store + a check-history-before-mutating guard.
n8n -- The workflow automation platform
License
MIT
ellmos-ai Ecosystem
This MCP server is part of the ellmos-ai ecosystem — AI infrastructure, MCP servers, and intelligent tools.
MCP Server Family
Server | Tools | Focus | npm |
46 | Filesystem, process management, interactive sessions, cloud-lock-safe operations | ||
22 | Code analysis, JSON repair, imports, diffs, regex | ||
12 | File repair, format conversion, batch operations | ||
18 | n8n workflow management via AI assistants | ||
20 | MCP stack discovery, profile management, control plane | ||
45 | Local-first LLM memory, knowledge, state, routing, swarm orchestration |
| |
8 | Server operations: health checks, log analysis, deploy dry-runs, mail diagnostics |
| |
3 | Headless Blender asset QA and FBX reimport verification |
| |
10 | Model-agnostic computer use: capture, safety-gated actions, Windows UIA |
|
AI Infrastructure
Project | Description |
Local-first text-based OS for LLM agents — 113+ handlers, 550+ tools, SQLite memory | |
Model-agnostic computer-use core powering Open Compute MCP | |
Provider-neutral LLM orchestration with auto-routing and budget tracking | |
Lightweight agent memory, connectors, and automation infrastructure | |
Self-hosted AI research stack (Ollama + n8n + Rinnsal + KnowledgeDigest) | |
Autonomous agent chain framework for Claude Code | |
Minimalist database-driven LLM OS prototype (4 functions, 1 table) | |
Testing framework for LLM operating systems (7 dimensions) |
Desktop Software
Our partner organization open-bricks bundles AI-native desktop applications — a modern, open-source software suite built for the age of AI. Categories include file management, document tools, developer utilities, and more.
Haftung / Liability
Dieses Projekt ist eine unentgeltliche Open-Source-Schenkung im Sinne der §§ 516 ff. BGB. Die Haftung des Urhebers ist gemäß § 521 BGB auf Vorsatz und grobe Fahrlässigkeit beschränkt. Ergänzend gilt der Haftungsausschluss der MIT-Lizenz.
Nutzung auf eigenes Risiko. Keine Wartungszusage, keine Verfügbarkeitsgarantie, keine Gewähr für Fehlerfreiheit oder Eignung für einen bestimmten Zweck.
This project is an unpaid open-source donation under the MIT License. Liability is limited to intent and gross negligence (§ 521 German Civil Code). Use at your own risk. No warranty, no maintenance guarantee, no fitness-for-purpose assumed.
Maintenance
Related MCP Servers
- AlicenseAqualityDmaintenance🪄 MCP server for programmatic creation and management of n8n workflows. Enables AI assistants to build, modify, and manage workflows without direct user intervention through a comprehensive set of tools and resources for interacting with n8n's REST API.108184MIT
- Alicense-qualityDmaintenanceAn MCP server that provides AI assistants with access to documentation, schemas, and operations for over 535 n8n workflow automation nodes. It enables models to understand, create, and manage n8n workflows through natural language by connecting to the n8n API.160,284MIT
- Alicense-qualityDmaintenanceMCP server for n8n workflow automation, enabling management of workflows, executions, credentials, tags, users, and webhooks via an MCP-compatible client.MIT
- Alicense-qualityDmaintenanceMCP server for integrating with n8n, enabling workflow automation and management through natural language.2701MIT
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.
Create, browse, remix, collaborate on, and run durable AI workflow nodes from MCP hosts.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ellmos-ai/n8n-manager-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server