n8n Knowledge Index

Search real n8n templates and node settings, draft workflows in chat, check the structure before deploy, and push to your self-hosted instance — without copying JSON from forum posts.

For: Automation Leads, RevOps Builders, Integration Consultants, AI-First Operations Teams

1.9Knodes

Daily · last yesterday

47 tools

Chat with AI Use it from Claude, Cursor or ChatGPT →

Other ways to use n8n Workflow Builder

Same data, different audiences.

Chat & MCP

Use the same data from Claude, Cursor or ChatGPT. AI agents can call every tool the app uses.

Open Chat & MCP

Where the data comes from

Build n8n workflows with a materialized node and template knowledge index plus live workflow CRUD, execution, and management tools on the user's n8n instance.

Live snapshot

Records

1,917 nodes

Refresh cadence

Daily

Last refreshed

yesterday

Frequently Asked Questions

Do I need my own n8n instance?

Searching templates and checking drafts works without your instance. Deploying, running, and inspecting live workflows requires a connected n8n server with an access key from n8n Settings.

Where do the templates and node settings come from?

MCPBundles maintains a searchable index built from the public n8n template library and node catalog, refreshed on a schedule so agents query local evidence instead of hammering the public site on every turn.

Can it catch mistakes before a workflow goes live?

Yes. Drafts can be checked offline for missing node names, bad wiring, and common expression mistakes. After deploy, live checks and run inspection help repair failures without rebuilding from scratch.

Who is this for?

Ops and automation leads who already use n8n but want agents to search real examples, assemble drafts, and push to a self-hosted instance — not developers wiring custom integrations from memory.

How do I connect my n8n instance?

Enable the n8n Workflow Builder on MCPBundles, add your instance URL and access key from n8n Settings, then ask in chat. Knowledge search works immediately; deploy steps use the saved connection.

Use it from Claude, Cursor or ChatGPT

Same dataset, exposed as a Model Context Protocol server. Drop the URL into Claude Desktop, Cursor, VS Code, Cline, Windsurf, or any other MCP client.

MCP URL

https://mcp.mcpbundles.com/bundle/n8n-workflow-builder

Claude.ai Cursor VS Code VS Code Insiders Goose LM Studio Cherry Studio ChatGPT

One-click install:

Install on Claude.ai Install for organization (admins)

The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.

Or add manually

Open claude.ai → Settings → Connectors.
Click the + button and choose Add custom connector.
Set Name to n8n Knowledge Index and paste the MCP URL into Remote MCP server URL.
Click Add. n8n Knowledge Index will appear under Not connected — select it and click Connect to complete OAuth.

Name: n8n Knowledge Index

Remote MCP server URL: https://mcp.mcpbundles.com/bundle/n8n-workflow-builder

Authentication: OAuth

Custom connectors at claude.ai require a paid Claude plan (Pro, Max, Team, or Enterprise).

Full developer docs (skills page)