Skip to content
Back to search

n8n-mcp

A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/czlonkowski/n8n-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/czlonkowski/n8n-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/czlonkowski--n8n-mcp/badge.svg)](/listings/czlonkowski--n8n-mcp)

HTML

<a href="/listings/czlonkowski--n8n-mcp"><img src="/api/listings/czlonkowski--n8n-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 515 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # n8n-MCP
  2. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
  3. [![GitHub stars](https://img.shields.io/github/stars/czlonkowski/n8n-mcp?style=social)](https://github.com/czlonkowski/n8n-mcp)
  4. [![npm version](https://img.shields.io/npm/v/n8n-mcp.svg)](https://www.npmjs.com/package/n8n-mcp)
  5. [![codecov](https://codecov.io/gh/czlonkowski/n8n-mcp/graph/badge.svg?token=YOUR_TOKEN)](https://codecov.io/gh/czlonkowski/n8n-mcp)
  6. [![Tests](https://img.shields.io/badge/tests-6524%20passing-brightgreen.svg)](https://github.com/czlonkowski/n8n-mcp/actions)
  7. [![n8n version](https://img.shields.io/badge/n8n-2.46.7-orange.svg)](https://github.com/n8n-io/n8n)
  8. [![Docker](https://img.shields.io/badge/docker-ghcr.io%2Fczlonkowski%2Fn8n--mcp-green.svg)](https://github.com/czlonkowski/n8n-mcp/pkgs/container/n8n-mcp)
  9. [![OpenSSF Best Practices](https://www.bestpractices.dev/projects/16495/badge)](https://www.bestpractices.dev/projects/16495)
  10. [![Deploy on Railway](https://railway.com/button.svg)](https://railway.com/deploy/n8n-mcp?referralCode=n8n-mcp)
  11. n8n-MCP is an open-source MCP server that lets Claude, ChatGPT, Cursor, and other AI assistants operate n8n: read failed executions, edit workflows in place, validate and test them, manage credentials, and build new workflows. It works with any n8n instance that has the Public API enabled, and can use n8n's built-in MCP server as a second backend.
  12. ## What You Can Do With It
  13. - **Debug failing workflows** - `n8n_executions` reads an execution and, with `mode: "error"`, returns the error, the failing node, and sample items from the node before it.
  14. - **Edit workflows in place** - `n8n_update_partial_workflow` applies targeted operations to the nodes and connections named in the request, so the assistant does not resend the whole workflow. This includes find-and-replace inside one large field such as a Code node (`patchNodeField`). By default n8n-MCP saves a snapshot before it changes a workflow's nodes or connections, and `n8n_workflow_versions` can diff and roll back.
  15. - **Validate and fix before going live** - `validate_node`, `validate_workflow`, and `n8n_validate_workflow` report unknown nodes, invalid node versions, missing required fields, and broken connections or expressions. `n8n_autofix_workflow` repairs the common ones.
  16. - **Test** - `n8n_test_workflow` runs a workflow through its webhook, form, or chat trigger, or, through n8n's built-in MCP server, with pinned data when it has no such trigger.
  17. - **Manage the instance** - create, update, and delete credentials, work with data tables, folders and variables, and run a security audit (`n8n_audit_instance`).
  18. - **Build new workflows** - bundled knowledge of 3,501 nodes and 2,352 templates, so the assistant configures real nodes instead of guessing.
  19. - **Work across several n8n instances** - on the [hosted service](https://www.n8n-mcp.com/docs/multi-instance), register production, staging, and client instances once and name the target on each call. Self-hosted HTTP mode can serve several instances with [per-request instance headers](./docs/HTTP_DEPLOYMENT.md#per-request-instance-headers-multi-tenant).
  20. ## n8n-MCP and n8n's Built-In MCP Server
  21. n8n ships its own instance-level MCP server, and it covers a lot: building and editing workflows, executions, version history, data tables, and Agents. n8n-MCP does not replace it. The two differ in how they are built:
  22. | | n8n's built-in MCP server | n8n-MCP |
  23. |---|---|---|
  24. | Runs | Inside one n8n instance | As a separate server that talks to n8n |
  25. | Instances per connection | One | Several (hosted service, or multi-tenant HTTP mode) |
  26. | Credentials | Lists credentials and edits their descriptions | Creates, updates, and deletes credentials |
  27. | n8n versions | Present since late n8n 1.x; most tools need n8n 2.12 or later, and each tool has its own minimum version | Workflow and execution tools work through the Public API on older versions too, including the 1.x line. Credential actions depend on what that version's API exposes, and newer tools state the version they need |
  28. | Workflow access | Most operations need the workflow's "Available in MCP" setting, which is off by default | Every workflow the API key can reach |
  29. **The built-in server is enough when** you work with a single instance on a recent n8n 2.x, build and edit workflows on that instance, and set up credentials yourself in the n8n UI.
  30. **Add n8n-MCP when** you run more than one instance, want the assistant to create and update credentials, are on an older n8n version that predates the built-in tools you need, or want autofix, execution error analysis, templates, and a security audit.
  31. **Or use both through one connection.** Set `N8N_MCP_ACCESS_TOKEN` and n8n-MCP routes the operations the Public API cannot perform to n8n's own server: test runs with pinned data, n8n's native version history, live dropdown values, n8n Agents, and data-table column changes. The assistant still sees one MCP server. See [Official MCP Setup](./docs/OFFICIAL_MCP_SETUP.md).
  32. > **Naming note:** n8n's documentation uses `n8n-mcp` as the example connection name for its built-in server in some client configurations (for example `claude mcp add --transport http n8n-mcp https://<your-n8n-domain>/mcp-server/http`). That name points at n8n's own server. This project is a separate open-source server: `github.com/czlonkowski/n8n-mcp`, published on npm as `n8n-mcp`.
  33. ## Node and Template Coverage
  34. The documentation and validation tools work without an n8n connection, against a bundled database:
  35. - **3,501 n8n nodes** - 842 core nodes + 2,659 community nodes (2,228 verified)
  36. - **Node properties** - 99% coverage with detailed schemas
  37. - **Node operations** - 66.5% coverage of available actions
  38. - **Documentation** - 86% coverage from official n8n docs (including AI nodes)
  39. - **AI tools** - 267 AI-capable tool variants detected with full documentation
  40. - **Real-world examples** - 156 ranked configurations extracted from popular templates
  41. - **Template library** - 2,352 workflow templates with 99.96% AI metadata coverage
  42. - **Community nodes** - Search verified community integrations with `source` filter
  43. ## Support This Project
  44. <div align="center">
  45. <a href="https://github.com/sponsors/czlonkowski">
  46. <img src="https://img.shields.io/badge/Sponsor-❤️-db61a2?style=for-the-badge&logo=github-sponsors" alt="Sponsor n8n-mcp" />
  47. </a>
  48. </div>
  49. **n8n-mcp** started as a personal tool but now helps tens of thousands of developers automate their workflows efficiently. Maintaining and developing this project competes with my paid work. Your sponsorship helps me dedicate focused time to new features, respond quickly to issues, keep documentation up-to-date, and ensure compatibility with latest n8n releases. **[Become a sponsor](https://github.com/sponsors/czlonkowski)**
  50. > 💼 **Need it built for you?** Work with [AiAdvisors — n8n automation audits, builds, and operations](https://aiadvisors.pl/en), run by the author of n8n-mcp and n8n-skills.
  51. ## Working Safely on Live Workflows
  52. AI results can be unpredictable, and n8n-MCP can change real workflows. **Try changes to important production workflows on a copy or a staging instance first.**
  53. - **Snapshots and rollback** - by default n8n-MCP saves a version of a workflow before it changes its nodes or connections, and keeps up to 10 per workflow. `n8n_workflow_versions` lists, diffs, and rolls back those versions. A snapshot that fails to save does not stop the edit, so check that a version exists before relying on rollback for an important change.
  54. - **One editor at a time** - n8n-MCP reads a workflow, applies the change, and writes the whole workflow back, because n8n's Public API has no conditional write. An edit made in the n8n UI in between is overwritten, so do not edit a workflow in the UI while the assistant is working on it.
  55. - **Validate before deploying** - run `validate_workflow` on the change, and `n8n_validate_workflow` once it is in n8n.
  56. - **Keep exports** of workflows you cannot afford to lose.
  57. - **Limit what the assistant can do** - [Read-Only Deployment](#read-only-deployment) disables write operations.
  58. ## Quick Start
  59. **The fastest way to try n8n-MCP** - no installation, no configuration:
  60. **[dashboard.n8n-mcp.com](https://dashboard.n8n-mcp.com)**
  61. - Free tier: 100 tool calls/day
  62. - Instant access: Connect your n8n instance and start working on your workflows
  63. - Several n8n instances through one connection, on every plan ([multi-instance guide](https://www.n8n-mcp.com/docs/multi-instance))
  64. - OAuth sign-in for claude.ai and ChatGPT, API keys for IDEs and other MCP clients
  65. - Your n8n API key is stored encrypted and is never returned to the AI client
  66. - Always up-to-date: Latest n8n nodes and templates
  67. - No infrastructure: We handle everything
  68. The hosted service is run by the author of this project. Just sign up, connect your n8n instance, and connect your MCP client.
  69. **Want to self-host?** See the [Self-Hosting Guide](./docs/SELF_HOSTING.md) for npx, Docker, Railway, and local installation options.
  70. ## n8n Integration
  71. Want to use n8n-MCP with your n8n instance? Check out our comprehensive [n8n Deployment Guide](./docs/N8N_DEPLOYMENT.md) for:
  72. - Local testing with the MCP Client Tool node
  73. - Production deployment with Docker Compose
  74. - Cloud deployment on Hetzner, AWS, and other providers
  75. - Troubleshooting and security best practices
  76. ### Cloudflare Access Authentication
  77. If your n8n instance sits behind Cloudflare Access (Zero Trust), provide your service token so n8n-MCP can authenticate:
  78. - `N8N_CF_CLIENT_ID` - Cloudflare Access Client ID
  79. - `N8N_CF_CLIENT_SECRET` - Cloudflare Access Client Secret
  80. When set, these are sent as `CF-Access-Client-Id` / `CF-Access-Client-Secret` headers on n8n API requests, version/health probes, and webhook executions. The token is confined to the `N8N_API_URL` origin — webhook calls to a different host (e.g. a split `WEBHOOK_URL` origin) do not receive it, to avoid leaking the token.
  81. ### n8n Agents and Instance-Level MCP (Optional)
  82. To use `n8n_manage_agents`, `n8n_explore_node_resources`, and the project fallback in `n8n_list_catalog`, set:
  83. - `N8N_MCP_ACCESS_TOKEN` - MCP API key from n8n Settings → Instance-level MCP → set MCP status to Enabled. This is a separate secret from `N8N_API_KEY` and should be stored the same way. The MCP endpoint is derived from `N8N_API_URL`; instances that serve MCP from a split host (`N8N_MCP_BASE_URL`) are not supported.
  84. See [Connecting n8n-mcp to n8n's instance-level MCP server](./docs/OFFICIAL_MCP_SETUP.md) for the full setup walkthrough, including how to get the token from the n8n UI, prerequisites, and troubleshooting.
  85. ## Connect your IDE
  86. n8n-MCP works with multiple AI-powered IDEs and tools:
  87. - [Claude Code](./docs/CLAUDE_CODE_SETUP.md) - Quick setup for Claude Code CLI
  88. - [Visual Studio Code](./docs/VS_CODE_PROJECT_SETUP.md) - VS Code with GitHub Copilot integration
  89. - [Cursor](./docs/CURSOR_SETUP.md) - Step-by-step Cursor IDE setup
  90. - [Windsurf](./docs/WINDSURF_SETUP.md) - Windsurf integration with project rules
  91. - [Codex](./docs/CODEX_SETUP.md) - Codex integration guide
  92. - [Kiro](./docs/KIRO_SETUP.md) - Kiro IDE and CLI setup
  93. - [Antigravity](./docs/ANTIGRAVITY_SETUP.md) - Antigravity integration guide
  94. ## Add Claude Skills (Optional)
  95. Supercharge your n8n workflow building with specialized skills that teach AI how to build production-ready workflows!
  96. [![n8n-mcp Skills Setup](./docs/img/skills.png)](https://www.youtube.com/watch?v=e6VvRqmUY2Y)
  97. Learn more: [n8n-skills repository](https://github.com/czlonkowski/n8n-skills)
  98. ## Claude Project Setup
  99. For the best results when using n8n-MCP with Claude Projects, use these enhanced system instructions:
  100. ````markdown
  101. You are an expert in n8n automation software using n8n-MCP tools. Your role is to design, build, and validate n8n workflows with maximum accuracy and efficiency.
  102. ## Core Principles
  103. ### 1. Silent Execution
  104. CRITICAL: Execute tools without commentary. Only respond AFTER all tools complete.
  105. ### 2. Parallel Execution
  106. When operations are independent, execute them in parallel for maximum performance.
  107. ### 3. Templates First
  108. ALWAYS check templates before building from scratch (2,352 available).
  109. ### 4. Multi-Level Validation
  110. Use validate_node(mode='minimal') → validate_node(mode='full') → validate_workflow pattern.
  111. ### 5. Never Trust Defaults
  112. CRITICAL: Default parameter values are the #1 source of runtime failures.
  113. ALWAYS explicitly configure ALL parameters that control node behavior.
  114. ## Workflow Process
  115. 1. **Start**: Call `tools_documentation()` for best practices
  116. 2. **Template Discovery Phase** (FIRST - parallel when searching multiple)
  117. - `search_templates({searchMode: 'by_metadata', complexity: 'simple'})` - Smart filtering
  118. - `search_templates({searchMode: 'by_task', task: 'webhook_processing'})` - Curated by task
  119. - `search_templates({query: 'slack notification'})` - Text search (default searchMode='keyword')
  120. - `search_templates({searchMode: 'by_nodes', nodeTypes: ['n8n-nodes-base.slack']})` - By node type
  121. **Filtering strategies**:
  122. - Beginners: `complexity: "simple"` + `maxSetupMinutes: 30`
  123. - By role: `targetAudience: "marketers"` | `"developers"` | `"analysts"`
  124. - By time: `maxSetupMinutes: 15` for quick wins
  125. - By service: `requiredService: "openai"` for compatibility
  126. 3. **Node Discovery** (if no suitable template - parallel execution)
  127. - Think deeply about requirements. Ask clarifying questions if unclear.
  128. - `search_nodes({query: 'keyword', includeExamples: true})` - Parallel for multiple nodes
  129. - `search_nodes({query: 'trigger'})` - Browse triggers
  130. - `search_nodes({query: 'AI agent langchain'})` - AI-capable nodes
  131. 4. **Configuration Phase** (parallel for multiple nodes)
  132. - `get_node({nodeType, detail: 'standard', includeExamples: true})` - Essential properties (default)
  133. - `get_node({nodeType, detail: 'minimal'})` - Basic metadata only (~200 tokens)
  134. - `get_node({nodeType, detail: 'full'})` - Complete information (~3000-8000 tokens)
  135. - `get_node({nodeType, mode: 'search_properties', propertyQuery: 'auth'})` - Find specific properties
  136. - `get_node({nodeType, mode: 'docs'})` - Human-readable markdown documentation
  137. - Show workflow architecture to user for approval before proceeding
  138. 5. **Validation Phase** (parallel for multiple nodes)
  139. - `validate_node({nodeType, config, mode: 'minimal'})` - Quick required fields check
  140. - `validate_node({nodeType, config, mode: 'full', profile: 'runtime'})` - Full validation with fixes
  141. - Fix ALL errors before proceeding
  142. 6. **Building Phase**
  143. - If using template: `get_template(templateId, {mode: "full"})`
  144. - **MANDATORY ATTRIBUTION**: "Based on template by **[author.name]** (@[username]). View at: [url]"
  145. - Build from validated configurations
  146. - EXPLICITLY set ALL parameters - never rely on defaults
  147. - Connect nodes with proper structure
  148. - Add error handling
  149. - Use n8n expressions: $json, $node["NodeName"].json
  150. - Build in artifact (unless deploying to n8n instance)
  151. 7. **Workflow Validation** (before deployment)
  152. - `validate_workflow(workflow)` - Complete validation
  153. - `validate_workflow_connections(workflow)` - Structure check
  154. - `validate_workflow_expressions(workflow)` - Expression validation
  155. - Fix ALL issues before deployment
  156. 8. **Deployment** (if n8n API configured)
  157. - `n8n_create_workflow(workflow)` - Deploy
  158. - `n8n_validate_workflow({id})` - Post-deployment check
  159. - `n8n_update_partial_workflow({id, operations: [...]})` - Batch updates
  160. - `n8n_test_workflow({workflowId})` - Test workflow execution
  161. ## Critical Warnings
  162. ### Never Trust Defaults
  163. Default values cause runtime failures. Example:
  164. ```json
  165. // FAILS at runtime
  166. {resource: "message", operation: "post", text: "Hello"}
  167. // WORKS - all parameters explicit
  168. {resource: "message", operation: "post", select: "channel", channelId: "C123", text: "Hello"}
  169. ```
  170. ### Example Availability
  171. `includeExamples: true` returns real configurations from workflow templates.
  172. - Coverage varies by node popularity
  173. - When no examples available, use `get_node` + `validate_node({mode: 'minimal'})`
  174. ## Validation Strategy
  175. ### Level 1 - Quick Check (before building)
  176. `validate_node({nodeType, config, mode: 'minimal'})` - Required fields only (<100ms)
  177. ### Level 2 - Comprehensive (before building)
  178. `validate_node({nodeType, config, mode: 'full', profile: 'runtime'})` - Full validation with fixes
  179. ### Level 3 - Complete (after building)
  180. `validate_workflow(workflow)` - Connections, expressions, AI tools
  181. ### Level 4 - Post-Deployment
  182. 1. `n8n_validate_workflow({id})` - Validate deployed workflow
  183. 2. `n8n_autofix_workflow({id})` - Auto-fix common errors
  184. 3. `n8n_executions({action: 'list'})` - Monitor execution status
  185. ## Response Format
  186. ### Initial Creation
  187. ```
  188. [Silent tool execution in parallel]
  189. Created workflow:
  190. - Webhook trigger → Slack notification
  191. - Configured: POST /webhook → #general channel
  192. Validation: All checks passed
  193. ```
  194. ### Modifications
  195. ```
  196. [Silent tool execution]
  197. Updated workflow:
  198. - Added error handling to HTTP node
  199. - Fixed required Slack parameters
  200. Changes validated successfully.
  201. ```
  202. ## Batch Operations
  203. Use `n8n_update_partial_workflow` with multiple operations in a single call:
  204. GOOD - Batch multiple operations:
  205. ```json
  206. n8n_update_partial_workflow({
  207. id: "wf-123",
  208. operations: [
  209. {type: "updateNode", nodeId: "slack-1", changes: {...}},
  210. {type: "updateNode", nodeId: "http-1", changes: {...}},
  211. {type: "cleanStaleConnections"}
  212. ]
  213. })
  214. ```
  215. BAD - Separate calls:
  216. ```json
  217. n8n_update_partial_workflow({id: "wf-123", operations: [{...}]})
  218. n8n_update_partial_workflow({id: "wf-123", operations: [{...}]})
  219. ```
  220. ### CRITICAL: addConnection Syntax
  221. The `addConnection` operation requires **four separate string parameters**. Common mistakes cause misleading errors.
  222. CORRECT - Four separate string parameters:
  223. ```json
  224. {
  225. "type": "addConnection",
  226. "source": "node-id-string",
  227. "target": "target-node-id-string",
  228. "sourcePort": "main",
  229. "targetPort": "main"
  230. }
  231. ```
  232. **Reference**: [GitHub Issue #327](https://github.com/czlonkowski/n8n-mcp/issues/327)
  233. ### CRITICAL: IF Node Multi-Output Routing
  234. IF nodes have **two outputs** (TRUE and FALSE). Use the **`branch` parameter** to route to the correct output:
  235. ```json
  236. n8n_update_partial_workflow({
  237. id: "workflow-id",
  238. operations: [
  239. {type: "addConnection", source: "If Node", target: "True Handler", sourcePort: "main", targetPort: "main", branch: "true"},
  240. {type: "addConnection", source: "If Node", target: "False Handler", sourcePort: "main", targetPort: "main", branch: "false"}
  241. ]
  242. })
  243. ```
  244. **Note**: Without the `branch` parameter, both connections may end up on the same output, causing logic errors!
  245. ### removeConnection Syntax
  246. Use the same four-parameter format:
  247. ```json
  248. {
  249. "type": "removeConnection",
  250. "source": "source-node-id",
  251. "target": "target-node-id",
  252. "sourcePort": "main",
  253. "targetPort": "main"
  254. }
  255. ```
  256. ## Important Rules
  257. ### Core Behavior
  258. 1. **Silent execution** - No commentary between tools
  259. 2. **Parallel by default** - Execute independent operations simultaneously
  260. 3. **Templates first** - Always check before building (2,352 available)
  261. 4. **Multi-level validation** - Quick check → Full validation → Workflow validation
  262. 5. **Never trust defaults** - Explicitly configure ALL parameters
  263. ### Attribution & Credits
  264. - **MANDATORY TEMPLATE ATTRIBUTION**: Share author name, username, and n8n.io link
  265. - **Template validation** - Always validate before deployment (may need updates)
  266. ### Code Node Usage
  267. - **Avoid when possible** - Prefer standard nodes
  268. - **Only when necessary** - Use code node as last resort
  269. - **AI tool capability** - ANY node can be an AI tool (not just marked ones)
  270. ### Most Popular n8n Nodes (for get_node):
  271. 1. **n8n-nodes-base.code** - JavaScript/Python scripting
  272. 2. **n8n-nodes-base.httpRequest** - HTTP API calls
  273. 3. **n8n-nodes-base.webhook** - Event-driven triggers
  274. 4. **n8n-nodes-base.set** - Data transformation
  275. 5. **n8n-nodes-base.if** - Conditional routing
  276. 6. **n8n-nodes-base.manualTrigger** - Manual workflow execution
  277. 7. **n8n-nodes-base.respondToWebhook** - Webhook responses
  278. 8. **n8n-nodes-base.scheduleTrigger** - Time-based triggers
  279. 9. **@n8n/n8n-nodes-langchain.agent** - AI agents
  280. 10. **n8n-nodes-base.googleSheets** - Spreadsheet integration
  281. 11. **n8n-nodes-base.merge** - Data merging
  282. 12. **n8n-nodes-base.switch** - Multi-branch routing
  283. 13. **n8n-nodes-base.telegram** - Telegram bot integration
  284. 14. **@n8n/n8n-nodes-langchain.lmChatOpenAi** - OpenAI chat models
  285. 15. **n8n-nodes-base.splitInBatches** - Batch processing
  286. 16. **n8n-nodes-base.openAi** - OpenAI legacy node
  287. 17. **n8n-nodes-base.gmail** - Email automation
  288. 18. **n8n-nodes-base.function** - Custom functions
  289. 19. **n8n-nodes-base.stickyNote** - Workflow documentation
  290. 20. **n8n-nodes-base.executeWorkflowTrigger** - Sub-workflow calls
  291. **Note:** LangChain nodes use the `@n8n/n8n-nodes-langchain.` prefix, core nodes use `n8n-nodes-base.`
  292. ````
  293. Save these instructions in your Claude Project for optimal n8n workflow assistance with intelligent template discovery.
  294. ## Available MCP Tools
  295. ### Core Tools (7 tools)
  296. - **`tools_documentation`** - Get documentation for any MCP tool (START HERE!)
  297. - **`search_nodes`** - Full-text search across all nodes. Use `source: 'community'|'verified'` for community nodes, `includeExamples: true` for configs
  298. - **`get_node`** - Unified node information tool with multiple modes:
  299. - **Info mode** (default): `detail: 'minimal'|'standard'|'full'`, `includeExamples: true`
  300. - **Docs mode**: `mode: 'docs'` - Human-readable markdown documentation
  301. - **Property search**: `mode: 'search_properties'`, `propertyQuery: 'auth'`
  302. - **Versions**: `mode: 'versions'|'compare'|'breaking'|'migrations'`
  303. - **`validate_node`** - Unified node validation:
  304. - `mode: 'minimal'` - Quick required fields check (<100ms)
  305. - `mode: 'full'` - Comprehensive validation with profiles (minimal, runtime, ai-friendly, strict)
  306. - **`validate_workflow`** - Complete workflow validation including AI Agent validation
  307. - **`search_templates`** - Unified template search:
  308. - `searchMode: 'keyword'` (default) - Text search with `query` parameter
  309. - `searchMode: 'by_nodes'` - Find templates using specific `nodeTypes`
  310. - `searchMode: 'by_task'` - Curated templates for common `task` types
  311. - `searchMode: 'by_metadata'` - Filter by `complexity`, `requiredService`, `targetAudience`
  312. - **`get_template`** - Get complete workflow JSON (modes: nodes_only, structure, full)
  313. ### n8n Management Tools (22 tools - Requires API Configuration)
  314. These tools require `N8N_API_URL` and `N8N_API_KEY` in your configuration.
  315. #### Workflow Management
  316. - **`n8n_create_workflow`** - Create new workflows with nodes and connections
  317. - **`n8n_get_workflow`** - Unified workflow retrieval (modes: full, details, structure, minimal)
  318. - **`n8n_update_full_workflow`** - Update entire workflow (complete replacement)
  319. - **`n8n_update_partial_workflow`** - Update workflow using diff operations
  320. - **`n8n_delete_workflow`** - Delete workflows permanently
  321. - **`n8n_list_workflows`** - List workflows with filtering and pagination
  322. - **`n8n_validate_workflow`** - Validate workflows in n8n by ID
  323. - **`n8n_autofix_workflow`** - Automatically fix common workflow errors
  324. - **`n8n_workflow_versions`** - Version history, diff and rollback over two histories: `source: 'local'` (the snapshots n8n-mcp takes before it changes a workflow, the default) and `source: 'native'` (n8n's own workflow history, including UI edits — needs `N8N_MCP_ACCESS_TOKEN` and the workflow's "Available in MCP" setting)
  325. - **`n8n_deploy_template`** - Deploy templates from n8n.io directly to your instance with auto-fix
  326. #### Node Resource Discovery
  327. - **`n8n_explore_node_resources`** - Resolve a node's dynamic dropdown (loadOptions) or resource-locator search (listSearch) values — Slack channels, Google Sheets tabs, model lists — using a real credential, so workflow configs use existing IDs instead of invented ones. Requires `N8N_MCP_ACCESS_TOKEN` (see [Official MCP Setup](./docs/OFFICIAL_MCP_SETUP.md))
  328. #### Execution Management
  329. - **`n8n_test_workflow`** - Run a workflow. `method: 'auto'` (default) triggers it over HTTP through its webhook/form/chat trigger; `method: 'prepare'`/`'pinned'`/`'direct'` run workflows that have no such trigger through n8n's own MCP server (needs `N8N_MCP_ACCESS_TOKEN` and the workflow's "Available in MCP" setting)
  330. - **`n8n_executions`** - Unified execution management (list, get, delete)
  331. - **`n8n_evaluations`** - Run and read evaluation test runs (list runs, aggregated metrics, per-case results on n8n 2.30+; trigger and cancel on 2.32+)
  332. #### Folder Management
  333. - **`n8n_manage_folders`** - Manage workflow folders (create, list, get, rename, move, delete; n8n 2.19+). Place workflows into folders via `n8n_create_workflow`'s `parentFolderId` or `n8n_update_partial_workflow`'s `moveToFolder` operation (n8n 2.32+)
  334. #### Variable Management
  335. - **`n8n_manage_variables`** - Manage instance variables that workflows read as `{{ $vars.KEY }}` (list, get, create, update, delete; global or project-scoped). Needs an n8n license that includes Variables; set `DISABLE_ENTERPRISE_TOOLS=true` to hide it on Community-edition instances
  336. #### Data Table Management
  337. - **`n8n_manage_datatable`** - Manage n8n data tables, rows and columns (list, get, create, update, delete; `addColumn`/`deleteColumn`/`renameColumn` change an existing table's columns through n8n's own MCP server and need `N8N_MCP_ACCESS_TOKEN`)
  338. #### Credential Management
  339. - **`n8n_manage_credentials`** - Manage n8n credentials (list, get, create, update, delete, getSchema)
  340. #### Security & Audit
  341. - **`n8n_audit_instance`** - Security audit combining n8n's built-in audit API with deep workflow scanning
  342. #### Agents
  343. - **`n8n_manage_agents`** - Manage n8n Agents (persisted assistants with a model, instructions, tools, skills, tasks, memory and channels) through n8n's instance-level MCP server. Requires `N8N_MCP_ACCESS_TOKEN` and n8n 2.34+ with the agents module (see [Official MCP Setup](./docs/OFFICIAL_MCP_SETUP.md)). This is not the AI Agent workflow node — use `get_node` for that
  344. #### System Tools
  345. - **`n8n_health_check`** - Check n8n API connectivity and features, including `officialMcp` status when `N8N_MCP_ACCESS_TOKEN` is configured
  346. - **`n8n_list_catalog`** - List instance-level projects or tags; falls back to n8n's instance-level MCP server for team projects when the Public API doesn't expose them
  347. ### Read-Only Deployment
  348. For governance-sensitive environments, use both env vars together. Fully disable tools that are write/destructive or handle sensitive data (`n8n_manage_credentials` and `n8n_manage_datatable` also offer read operations, but are removed entirely here because even reads expose sensitive material):
  349. ```bash
  350. DISABLED_TOOLS=n8n_create_workflow,n8n_update_full_workflow,n8n_update_partial_workflow,n8n_delete_workflow,n8n_autofix_workflow,n8n_deploy_template,n8n_test_workflow,n8n_manage_credentials,n8n_manage_datatable
  351. ```
  352. For tools that bundle read and write operations under one name, block only the destructive operations while keeping `list` and `get`. Use this instead of a full `DISABLED_TOOLS` entry where the tool's read operations are acceptable — the `n8n_manage_datatable` and `n8n_test_workflow` entries below are the alternative to removing those tools entirely as above. The example names every write operation of every tool that has one:
  353. ```bash
  354. DISABLED_TOOL_OPERATIONS=n8n_executions:delete;n8n_test_workflow:auto,trigger,pinned,direct,expose;n8n_evaluations:run,cancel;n8n_manage_folders:create,rename,move,delete;n8n_manage_variables:create,update,delete;n8n_workflow_versions:delete,rollback,prune,expose;n8n_manage_agents:create,mutate,call,publish,unpublish,revert,delete,update_integration;n8n_manage_datatable:createTable,updateTable,deleteTable,insertRows,updateRows,upsertRows,deleteRows,addColumn,deleteColumn,renameColumn
  355. ```
  356. Two details are easy to miss when writing your own list. For `n8n_test_workflow`, all four of `auto`, `trigger`, `pinned` and `direct` run the workflow (an omitted or blank `method` counts as `auto`), leaving only the read-only `prepare`. And `expose` is not a value of any operation parameter: it is the `exposeToMcp` consent write of `n8n_test_workflow` and `n8n_workflow_versions`, which enables a workflow's "Available in MCP" setting. Omitting `expose` leaves that write reachable.
  357. Combine with a read-only n8n API key (Settings → API in your n8n instance) for defence in depth. See [Read-Only Deployment Recipe](./docs/HTTP_DEPLOYMENT.md#read-only-deployment-recipe) for the full setup guide.
  358. ## Documentation
  359. - [Self-Hosting Guide](./docs/SELF_HOSTING.md) - npx, Docker, Railway, and local installation
  360. - [Security & Hardening](./docs/SECURITY_HARDENING.md) - Trust model, hardening options, workflow restrictions
  361. - [n8n Deployment Guide](./docs/N8N_DEPLOYMENT.md) - Production deployment with n8n
  362. - [Database Configuration](./docs/DATABASE_CONFIGURATION.md) - SQLite adapters and memory optimization
  363. - [Privacy & Telemetry](./PRIVACY.md) - What we collect and how to opt out
  364. - [Workflow Diff Operations](./docs/workflow-diff-examples.md) - Token-efficient workflow updates
  365. - [HTTP Deployment](./docs/HTTP_DEPLOYMENT.md) - Remote server setup
  366. - [Official MCP Setup](./docs/OFFICIAL_MCP_SETUP.md) - Connect n8n-mcp to n8n's instance-level MCP server for Agents and node resource discovery
  367. - [Change Log](./CHANGELOG.md) - Complete version history
  368. ## License
  369. MIT License - see [LICENSE](LICENSE) for details.
  370. ## Contributing
  371. See [CONTRIBUTING.md](./CONTRIBUTING.md) for development setup, testing, and contribution guidelines.
  372. ## Acknowledgments
  373. See [Acknowledgments](./docs/ACKNOWLEDGMENTS.md) for credits and template attribution.
  374. ---
  375. <div align="center">
  376. <strong>Built with care for the n8n community</strong>
  377. </div>
  378. ---
  379. > 💼 **Need it built for you?**
  380. >
  381. > Work with [AiAdvisors — n8n automation audits, builds, and operations](https://aiadvisors.pl/en), run by the author of n8n-mcp and n8n-skills.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.