n8n Manager MCP Server

🇩🇪 Deutsche Version

Part of the ellmos-ai family and the open-bricks umbrella.

MCP (Model Context Protocol) server for managing n8n workflows via AI assistants like Claude, Cursor, and Windsurf.

The n8n Manager MCP Server operates as a local-first, stdio-connected bridge between AI development environments (Claude Code, Claude Desktop, Cursor, Windsurf) and local or remote n8n instances.

• Process Model: Runs purely in user space (RunAsInvoker) as a dedicated Node.js child process communicating via standard input/output (stdio) using JSON-RPC 2.0.
• Fail-Closed Safety Middleware: Every mutation tool call passes through an immutable safety gate before contacting n8n APIs or touching the filesystem.
• Multi-Instance Router: Seamlessly targets independent n8n instances (development, staging, production) with isolated API credentials and atomic configuration persistence.
• Offline Node Catalog: Provides instantaneous node schema introspection (n8n_describe_nodes) without incurring API latency or network calls.

+========================================================================================================+
| [VIEW 1: CALLER RUNTIMES & AGENT ECOSYSTEM]                                                           |
| Claude Code CLI      | Claude Desktop      | Cursor IDE / Windsurf | Antigravity / Gemini / Codex     |
| (JSON-RPC 2.0 Stdio) | (stdio MCP Client)  | (Dev Environments)    | (Autonomous Orchestrator Swarms) |
+===================================================+====================================================+
                                                    |
                                                    v
+========================================================================================================+
| [VIEW 2: N8N-MANAGER-MCP CORE ENGINE & SAFETY ARBITRATION]                                             |
| +----------------------------------------------------------------------------------------------------+ |
| | Tool Dispatcher (19 Registered MCP Tools: CRUD, Execution Inspect, Backup/Restore, Node Catalog)   | |
| +----------------------------------------------------------------------------------------------------+ |
| | Fail-Closed Safety Filter: N8N_MANAGER_READ_ONLY Enforcement (INV-READ-02)                          | |
| | Input Validation & Sanitization: Zod Schema Numeric Bounds & Path Traversal Guards (INV-TRAV-06)   | |
| | Multi-Instance Routing Engine: Development / Staging / Production Credentials Isolation (INV-SRV-05)| |
| | Bundled Offline Node Catalog: In-Memory Node Schemas & Parameter Introspection (INV-NODE-09)        | |
| +----------------------------------------------------------------------------------------------------+ |
+===================================================+====================================================+
                                                    |
                                                    v
+========================================================================================================+
| [VIEW 3: RUNTIME PERSISTENCE, BACKUP SNAPSHOTS & LOCAL AUDIT WAL]                                      |
| +------------------------------------+----------------------------------+----------------------------+ |
| | Pre-Mutation Workflow Snapshots    | Append-Only Local Audit Trail    | Multi-Server Config Store  | |
| | ~/.n8n-manager-mcp/backups/        | ~/.n8n-manager-mcp/audit.log     | ~/.n8n-manager-mcp/        | |
| | ({server}/{id}-{timestamp}.json)   | (Forensic Timestamped Log)       | (servers.json, 0600 mode)  | |
| +------------------------------------+----------------------------------+----------------------------+ |
+===================================================+====================================================+
                                                    |
                                                    v
+========================================================================================================+
| [VIEW 4: DEFENSE PERIMETER, ZERO-EGRESS & RUNASINVOKER]                                                |
| Standard User Mode (RunAsInvoker: Non-Elevation INV-PRIV-07) | Zero Outbound Telemetry / Ad Tracking  |
| Local Loopback Binding (127.0.0.1 Default INV-LOCAL-01)      | SLA & Vulnerability Protocol (INV-SLA-10) |
+========================================================================================================+

flowchart TD
    Client["AI Client (Claude Code / Desktop / Cursor / Windsurf)"] -->|"MCP Stdio Protocol (JSON-RPC 2.0)"| Router["Tool Router (19 Tools)"]
    subgraph MCPServer["n8n Manager MCP Server (Local Stdio Process)"]
        Router --> Safety["Safety Layer (Read-Only Gate & Traversal Guard)"]
        Safety --> Backup["Pre-Mutation Snapshot Engine"]
        Safety --> MultiServer["Multi-Server Manager"]
        Safety --> Catalog["Offline Node Catalog (n8n_describe_nodes)"]
        Backup --> Audit["Append-Only Audit Logger"]
    end
    MultiServer -->|"REST API (API Key / Auth Header)"| LocalInst["Local n8n Instance (127.0.0.1:5678)"]
    MultiServer -->|"REST API (HTTPS / Token)"| CloudInst["Remote / Cloud n8n Instance"]
    Backup --> BackupFS[("Backups (~/.n8n-manager-mcp/backups/)")]
    Audit --> AuditFS[("Audit Log (~/.n8n-manager-mcp/audit.log)")]

sequenceDiagram
    autonumber
    actor AI as AI Assistant (Claude / Cursor)
    participant MCP as n8n-manager-mcp Router
    participant Safety as Safety & Read-Only Gate
    participant Snapshot as Backup Engine
    participant Store as Local Storage (~/.n8n-manager-mcp)
    participant N8N as n8n REST API Instance
    participant Audit as Forensic Audit Logger

    AI->>MCP: Call Mutation Tool (n8n_update_workflow / n8n_delete_workflow)
    MCP->>Safety: Check N8N_MANAGER_READ_ONLY
    alt Read-Only Active (INV-READ-02)
        Safety-->>AI: Blocked: Read-only mode active (Fail-Closed)
        Safety->>Audit: Record blocked mutation attempt
    else Mutation Permitted
        Safety->>Snapshot: Trigger Pre-Mutation Snapshot (INV-BACK-03)
        Snapshot->>N8N: GET /workflows/{id} (Fetch current state)
        N8N-->>Snapshot: Current Workflow JSON
        Snapshot->>Store: Save timestamped backup (~/backups/{server}/{id}-{timestamp}.json)
        Snapshot-->>Safety: Backup verified & path resolved
        Safety->>N8N: Execute Mutation (PUT / DELETE / PATCH)
        N8N-->>Safety: Mutation Response (200 OK / Updated ID)
        Safety->>Audit: Append structured forensic receipt (INV-AUDIT-04)
        Safety-->>AI: Success response with backup path & rollback receipt
    end

• npm package: published as n8n-manager-mcp
• Glama listing: public directory page for the ellmos-ai repo
• Enterprise DNA directory: additional public directory entry for ellmos-ai/n8n-manager-mcp
• PulseMCP listing: indexed as ellmos-ai-n8n-manager
• MCP namespace status: this repo contains server.json and mcpName metadata for io.github.ellmos-ai/n8n-manager-mcp; some ecosystem directories still expose the legacy io.github.lukisch/n8n-manager-mcp name until their indexes refresh.
• Search context: best matched by n8n MCP server, n8n workflow management MCP, AI assistant n8n workflows, and ellmos-ai n8n-manager-mcp.

• n8n mcp server claude code
• ai assistant n8n workflow management
• local-first n8n mcp stdio
• safe n8n automated workflow mutation
• n8n multi-server workflow sync mcp
• n8n describe nodes offline catalog
• zero-egress n8n agent automation
• modelcontextprotocol n8n typescript

• 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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "n8n-manager": {
      "command": "npx",
      "args": ["-y", "n8n-manager-mcp"]
    }
  }
}

claude mcp add --scope user n8n-manager npx -y n8n-manager-mcp

npm install -g n8n-manager-mcp

After installation, use these commands in your AI assistant:

1. Add your n8n server:

   "Add my n8n server at http://localhost:5678 with API key abc123"

2. List workflows:

   "Show me all workflows on my n8n server"

3. Create a workflow:

   "Create an n8n workflow that triggers on a webhook, fetches data from an API, and sends a Slack message"

4. Check executions:

   "Show me the last 10 workflow executions"

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_history reads from the running manager. Omit workflow_id to 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_status reports 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.

Numeric guardrails are part of the MCP schemas: workflow, execution, and backup list limits are finite positive integers from 1 to 1000 (the existing defaults remain 100, 20, and 20), and workflow connection from_output/ to_input indices are finite non-negative integers from 0 to 1000. Invalid values are rejected before any n8n API, filesystem, or workflow-array access.

Server connections and safety settings are stored in ~/.n8n-manager-mcp/servers.json.

Safety defaults:

• backup_before_mutations: true saves workflow JSON before update, delete, activate/deactivate, and overwrite-restore operations.
• audit_log: true appends mutation outcomes to ~/.n8n-manager-mcp/audit.log.
• read_only: false can be enabled with n8n_set_safety_mode or N8N_MANAGER_READ_ONLY=1. The environment flag is an enforcement ceiling: while it is enabled, persisted settings and n8n_set_safety_mode cannot 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 .json backups.
• n8n_add_server validates server connection input before saving: URLs must be http or https base URLs without embedded credentials, query strings, or fragments, and API keys must not contain whitespace.
• n8n_add_server default semantics are explicit: the first server becomes default; an update without is_default preserves the existing flag; true promotes the server; false intentionally removes its flag, after which default lookup falls back to the first configured server.

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 discovery

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)

The current verification record covers Windows locally and Ubuntu Linux in GitHub Actions; GitHub Actions runs build, test, and npm package checks on Node.js 20, 22, and 24. The commit-specific local record is kept in CHANGELOG.md. 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.

Contributions are welcome! Please review CONTRIBUTING.md for full guidelines, including:

• 10 Governance & Runtime Invariants (INV-LOCAL-01 to INV-SLA-10): 100% Local-First, Zero-Egress, monotonic read-only gates, and automated backups.
• Unprivileged User Mode (RunAsInvoker): Zero administrative elevation requested.
• Plan D Workflow: Development strictly against canonical local clones and GitHub origin/main.
• 48h Security Response SLA: Coordinated vulnerability disclosure via security@ellmos.ai and security@open-bricks.org.

• 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

MIT

This MCP server is part of the ellmos-ai ecosystem — AI infrastructure, MCP servers, and intelligent tools.

Our partner organization open-bricks and sister suites bundle AI-native desktop applications and developer utilities:

This project is licensed under the MIT License with attribution declared in NOTICE. To guarantee complete supply chain integrity and compliance in enterprise and autonomous agent environments, all dependencies are continuously audited:

• Zero Copyleft / AGPL: Contains no viral copyleft or unreviewed commercial dependencies.
• Zero External Telemetry: Emits no network beacons, analytics payloads, or external phone-home pings.
• Detailed Open-Source Inventory: Complete attribution notices, license texts, and transitive dependency analyses are available in THIRD_PARTY_LICENSES.md.
• Level 1 SBOM Plain-Text Companion: Complete machine-readable audit trail, non-elevation certification, and license companion available in THIRD_PARTY_LICENSES.txt.

For marketing positioning, target persona definitions, governance invariant mappings, and the 3-phase discoverability roadmap, see MARKETING-LOG.txt.

See CHANGELOG.md for detailed version history, release notes, and past migration milestones.

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.

As codified in SECURITY.md, we maintain a strict binding security policy:

• Initial Response SLA: Guaranteed within 48 hours (INV-SLA-10).
• Triage Commitment: Vulnerability assessment completed within 5 business days.
• Remediation SLA: Coordinated security patches delivered within 30 calendar days.
• Direct Contact Endpoints:
  • security@open-bricks.org
  • security@ellmos.ai
  • lukas@open-bricks.org