No — works against n8n Cloud too. Pass the cloud API URL (https://app.n8n.cloud/api/v1) and a cloud-issued API key.

Can the agent edit workflows?

Not by design. Workflow definitions are versioned config — editing through an agent loop is too easy to break. Edit in the n8n UI; trigger from the MCP.

How are credentials handled?

The n8n side owns credentials. The MCP token only gives access to trigger workflows and read run status — it never touches the credentials each workflow uses internally.

Whatever your n8n deployment enforces. The MCP itself does no throttling — pair with sensible API rate limits if many agents share one instance.

n8n (MCP archived)

Name: Top MCPs — curated MCP directory
Creator: Top MCPs
License: https://creativecommons.org/licenses/by/4.0/

Archived

Trigger and manage n8n workflows from an AI agent. Community MCP wrapper archived; n8n itself is unaffected.

Score 64(?)CommunityMIT 1.6kVerified May 27, 2026Top MCPs for Automation & Workflows →

Install View on GitHub

Quick answer

What it does

Connects to an n8n instance and exposes workflow listing, manual triggering, execution status, and run inspection to AI models.

Best for

Triggering existing n8n workflows
Checking execution status from chat
Inspecting failed runs
Listing available workflows

Not for

Workflow authoring (use the n8n UI)
High-frequency event-driven triggers (use n8n webhooks directly)

Setup recipe

Pick your client, then follow the three steps.

Install

claude_desktop_config.jsonjson

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": [
        "-y",
        "@leonardsellem/n8n-mcp-server"
      ],
      "env": {
        "N8N_API_URL": "${N8N_API_URL}",
        "N8N_API_KEY": "${N8N_API_KEY}"
      }
    }
  }
}

Paste under mcpServers. Fully quit and reopen Claude after editing.

CLI or .mcp.jsonshell

# export N8N_API_URL=https://n8n.example.com/api/v1
# export N8N_API_KEY=your-api-key
claude mcp add n8n -- npx -y @leonardsellem/n8n-mcp-server

Run from your repo. Commit .mcp.json to share with your team.

.cursor/mcp.jsonjson

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": [
        "-y",
        "@leonardsellem/n8n-mcp-server"
      ],
      "env": {
        "N8N_API_URL": "${N8N_API_URL}",
        "N8N_API_KEY": "${N8N_API_KEY}"
      }
    }
  }
}

Global path: ~/.cursor/mcp.json. Reload window after editing.

.vscode/mcp.jsonjsonc

{
  "servers": {
    "n8n": {
      "command": "npx",
      "args": [
        "-y",
        "@leonardsellem/n8n-mcp-server"
      ],
      "env": {
        "N8N_API_URL": "${N8N_API_URL}",
        "N8N_API_KEY": "${N8N_API_KEY}"
      }
    }
  }
}

VS Code uses the "servers" key (not "mcpServers").

~/.codeium/windsurf/mcp_config.jsonjson

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": [
        "-y",
        "@leonardsellem/n8n-mcp-server"
      ],
      "env": {
        "N8N_API_URL": "${N8N_API_URL}",
        "N8N_API_KEY": "${N8N_API_KEY}"
      }
    }
  }
}

Open via Cascade → hammer icon → Configure.

cline_mcp_settings.jsonjson

{
  "mcpServers": {
    "n8n": {
      "command": "npx",
      "args": [
        "-y",
        "@leonardsellem/n8n-mcp-server"
      ],
      "env": {
        "N8N_API_URL": "${N8N_API_URL}",
        "N8N_API_KEY": "${N8N_API_KEY}"
      }
    }
  }
}

Open via the Cline sidebar → MCP Servers → Edit.

~/.continue/config.jsonjson

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "npx",
          "args": [
            "-y",
            "@leonardsellem/n8n-mcp-server"
          ],
          "env": {
            "N8N_API_URL": "${N8N_API_URL}",
            "N8N_API_KEY": "${N8N_API_KEY}"
          }
        }
      }
    ]
  }
}

Continue uses modelContextProtocolServers with a transport block.

~/.codex/config.tomlshell

# ~/.codex/config.toml
[mcp_servers.n8n]
command = "npx"
args = [
  "-y",
  "@leonardsellem/n8n-mcp-server",
]
env = { N8N_API_URL = "${N8N_API_URL}", N8N_API_KEY = "${N8N_API_KEY}" }

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

~/.config/zed/settings.jsonjsonc

{
  "context_servers": {
    "n8n": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "@leonardsellem/n8n-mcp-server"
        ]
      },
      "env": {
        "N8N_API_URL": "${N8N_API_URL}",
        "N8N_API_KEY": "${N8N_API_KEY}"
      }
    }
  }
}

Zed calls them "context_servers". Settings live-reload on save.

ChatGPT → Apps directorynone

n8n (MCP archived) doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

2
Set required secrets
Set N8N_API_URL, N8N_API_KEY in your shell environment before launching your MCP client.
3
Try a minimum working prompt
Minimum working prompt pending verification. Try any prompt from the MCP’s README once installed.

Tools & permissions

Tools list pending verification. The server exposes tools over MCP; we haven’t yet parsed its capability manifest into this page. Check the GitHub repo for the authoritative list.

Security & scope

Access scope: Network
Sandbox: n8n API key in env. The key inherits the user it was issued for; scope by creating a dedicated n8n user for the MCP with only the workflows it needs to trigger.
Gotchas: Triggering production workflows from chat is action-taking — require user confirmation in the client.
Run logs may contain sensitive data from the workflows themselves. Treat the audit trail as the source of truth.
API keys are long-lived; rotate per the standard playbook.

Agent prompt pack

— copy into Claude, Cursor, or ChatGPT.

Paste into Claude, Cursor, or ChatGPT. Edit the [brackets] before sending.

Recommend the best MCP servers for [task: e.g. automation & workflows work] in [client: Claude].

Constraints:
- Prefer tools that are [official | open-source | read-only] — pick what matters for my use case.
- Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport].
- Return at most 3 picks, ranked.

For each pick include:
1. One-sentence rationale.
2. The ready-to-paste install snippet for my client.
3. Any required secrets I need to create before installing.

Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-automation-workflows

Compare n8n (MCP archived) against a real alternative. Swap the second MCP in [brackets] if you want a different match.

Compare n8n (MCP archived) MCP vs [Zapier MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"].

Judge them on:
- Setup time and complexity (what a new user hits first).
- Auth model (none / API key / OAuth 2.1) and credential risk.
- Transport (stdio / Streamable HTTP / SSE) and where the server runs.
- Required secrets and the blast radius if they leak.
- Operational risk in an unattended agent loop.
- Which one is "good enough" for a weekend prototype vs. production.

End with one sentence: which should I pick for my scenario, which is: [my scenario].

References:
- https://top-mcps.com/mcp/n8n
- top-mcps.com listing for Zapier

Asks the agent to install and verify. Works inside Claude Code, Cursor Agent, Codex CLI.

Install the n8n (MCP archived) MCP server for my [client: Claude] at the default config path for that client.

Use the exact install snippet published at https://top-mcps.com/mcp/n8n (fetch https://top-mcps.com/mcp/n8n.json for the canonical server.json if you can read URLs).

Before finishing:
1. Create the required secrets (N8N_API_URL, N8N_API_KEY) and put them in the appropriate env block — do not hard-code them.
2. Restart or reload the client so it picks up the new server.
3. Verify the server is connected (green / running state) and at least one tool is listed.
4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry.

Confirm when done and list the tools the server now exposes.

Frequently asked questions

What changed

— 2 updates tracked.

May 27, 2026
Refreshed install snippets and fact sheet; verified for 2026.
Apr 12, 2025
Initial directory listing.

More Automation & Workflows MCPs

Other tools in the same category worth evaluating.

Zapier

Official

Expose 8,000+ Zapier integrations as tools your AI agent can call.

zapierautomationintegrationsworkflow

5 minLow

Make.com

Official

Turn Make.com on-demand scenarios into agent-callable tools — official MCP.

make-comautomationworkflowsintegromat

10 minMedium

Pipedream

Official

2,800+ apps and managed OAuth via Pipedream's hosted MCP at mcp.pipedream.com.

pipedreamautomationworkflowsoauth

10 minMedium

Compared with n8n (MCP archived)

Side-by-side breakdowns for the choices people most often weigh against this MCP.

n8n (MCP archived)vsZapier n8n (MCP archived)vsMake (Integromat)n8n (MCP archived)vsPipedream

Exploring Top MCPs for Automation & Workflows? See all Automation & Workflows MCPs →

Quick answer

What it does

Best for

Not for

Setup recipe

Install

Set required secrets

Try a minimum working prompt

Tools & permissions

Security & scope

Agent prompt pack

Full details

Frequently asked questions

Self-hosted only?

Can the agent edit workflows?

How are credentials handled?

Rate limits?

What changed

More Automation & Workflows MCPs

Zapier

Make.com

Pipedream

Compared with n8n (MCP archived)