n8n MCP Server

Built-in MCP server for n8n: search, execute, create, and edit workflows directly from any MCP-capable AI client.

Description

The n8n MCP Server is a built-in component of n8n — it is not a separate package but ships directly with n8n v1.x. It exposes a Streamable HTTP endpoint at /mcp-server/http and allows MCP-capable AI clients to access your n8n instance, search workflows, execute them, create new ones, and edit existing ones. The direct product link points to the official n8n documentation at docs.n8n.io; the repository n8n-io/n8n is the monorepo for the entire n8n project — the GitHub stars counted there (as of September 2026) refer to the project as a whole, not to the MCP server feature alone.

What is the n8n MCP Server

The n8n MCP Server is an instance-level MCP connection: a single connection covers the entire n8n instance. According to the provider, once enabled, MCP clients can search workflows, interact with and execute workflows marked as available for MCP, create new workflows and data tables, and edit existing workflows (editing available from n8n 2.13.0). This sets it apart from the MCP Server Trigger node, which operates within a single workflow and exposes fine-grained, workflow-specific tools. The built-in MCP Server targets scenarios where an AI agent needs to orchestrate multiple workflows across an instance or automatically build new automations. n8n hosts it on its own cloud platform (n8n Cloud) while also supporting self-hosted deployments on your own infrastructure — hence deployment_type = both.

Prerequisites

Using the n8n MCP Server requires: an n8n instance (n8n Cloud or self-hosted) running at minimum version 2.33.0 for the full feature set (per-client setup steps and allowed callback URLs), plus instance owner or admin permissions to enable it. Supported MCP clients include Claude Desktop, Claude Code, Cursor, Codex, and Lovable. On self-hosted instances, the MCP feature can be completely disabled using the environment variable N8N_DISABLED_MODULES=mcp. Older versions show a simplified setup screen without per-client steps. The free community edition of n8n includes the MCP server; n8n Cloud makes the feature available on all plans, though the scope may depend on the selected plan.

Features: Workflows, Agents, Data Tables

According to the provider, the n8n MCP Server exposes several groups of tools. Workflow execution tools allow starting workflows; execute_workflow defaults to production mode and runs the published version, with an optional manual mode to run the current unpublished version. Workflow editing tools (from n8n 2.13.0) allow creating and modifying workflows directly from the AI client. search_workflows can search all workflows the current user has access to but returns only previews, not full workflow data. Additionally, agents and data tables (when the agents feature is active on the instance) can be enabled for MCP clients. All MCP-capable clients connected to the same instance see the same enabled workflows — there is no per-client filtering; on the user level, standard user-scoped access control still applies.

Setup

To enable the MCP server, an instance owner or admin navigates to Settings > Instance-level MCP and selects Enable MCP access. The page then shows three sections: Connection details with MCP status and a Connect button, Access (showing how many workflows and optionally agents are exposed), and Connected clients. For client authentication, OAuth (recommended) and API key are available. The Connect a client dialog guides through client-specific steps for CLI clients (Claude Code, Codex, Gemini CLI), web clients (Claude.ai, ChatGPT), and IDE clients (Cursor, VS Code, Windsurf). For Claude Code via the command line, the install command looks like: claude mcp add --transport http n8n <your-instance-mcp-server-url>. After completing the OAuth sign-in, the connection is active. Individual workflows must then be manually enabled for MCP access.

Security and Data Access

According to the provider, MCP access applies equally to all connected clients — there is no way to restrict specific workflows to specific clients. Users can only see workflows they have permission to access. For self-hosted instances, n8n recommends using Allowed Callback URLs (available from 2.33.0) to restrict OAuth redirects to approved domains. Because the MCP server includes write tools for workflow creation and editing, only trusted clients should be connected. According to the provider, no workflow data is sent to third-party AI providers; the connected AI client controls what is forwarded to its model provider. Prompt injection through workflow names or descriptions controlled by an attacker is a theoretical risk and should be factored into access decisions.

FAQ

Is the n8n MCP Server free? The n8n source code (including the MCP server) is available under the Sustainable Use License on GitHub. n8n Cloud offers paid plans; the community edition can be self-hosted free of charge. Current pricing and plan details are published at n8n.io/pricing.

Can I control all workflows from the AI client? No. Workflows must be individually enabled for MCP access. search_workflows returns previews of all accessible workflows, but execute_workflow runs only published versions (or the current version in manual mode). Workflows that are not enabled for MCP cannot be executed through the MCP server.

What do the GitHub stars represent? The star count in this entry refers to the monorepo n8n-io/n8n, which contains the entire n8n project (core, UI, packages, nodes). The MCP server is an integrated component and does not have its own repository. The monorepo's popularity reflects the overall project, not the MCP feature alone.

Requirements

n8n instance (Cloud or self-hosted) from v2.33.0, instance owner or admin permissions, and an MCP-capable AI client (Claude Desktop, Cursor, Codex, etc.).

Installation instructions

What the n8n MCP Server is

The n8n MCP Server, developed by czlonkowski and published as open source on GitHub, is a Model Context Protocol server that gives AI assistants such as Claude comprehensive access to n8n's node documentation, properties, and operations. n8n itself is a workflow automation platform that lets you graphically connect processes between different services, for example automatically forwarding form submissions into a CRM system. Per the provider, the MCP server currently covers around 2,791 n8n nodes, of which 833 are core nodes and 1,958 are community nodes, with 86 percent documentation coverage and 99 percent property coverage. In practical terms, this means an AI assistant using this server can look up what settings a specific n8n node has, how to configure it correctly, and which example configurations already exist from real-world workflow templates.

Step 1: Prerequisites for setup

There are two basic ways to use it. The fastest path, per the provider, is the hosted service at dashboard.n8n-mcp.com, where you sign up, get an API key, and add it to your own MCP client without running any infrastructure yourself. Alternatively, the server can be self-hosted, for example via npx, Docker, or a cloud platform such as Railway. Self-hosting requires Node.js or a working Docker environment. Anyone who also wants to connect the server to a real n8n instance, for example to manage workflows directly, needs an n8n API key from the n8n settings and, if the instance-level MCP feature of n8n is used, a separate MCP access token.

Step 2: Setup step by step

First, the MCP client is configured, for example Claude Code, Cursor, or Windsurf, by adding the server endpoint or start command to the respective configuration file. For the hosted variant, an API key and a URL are usually enough. For the self-hosted variant, the server is started locally or in a container and reached over a local port. It can then be tested by asking the assistant about the properties of a specific n8n node or requesting suggestions for a particular automation. Anyone connecting the server to a production n8n environment should, per the provider, absolutely make a copy of the affected workflow first, work in a test environment, and export backups of important workflows before accepting any AI-generated changes.

Security and best practices

The provider explicitly warns against editing production workflows directly with AI assistance, since AI results can be unpredictable. Instead, it recommends testing changes in a development environment first and only moving them to production after validation. If the connected n8n instance sits behind an access layer such as Cloudflare Access, the server supports corresponding service tokens that are sent only to the configured API address, to avoid accidentally leaking credentials to other destinations. Anyone using n8n's instance-level MCP access should store the required access token separately from the regular API key and with the same level of care, since the two cover different permission levels.

Practical value in daily work

For teams making heavy use of n8n for automation, the server shortens the time otherwise spent looking up node documentation and experimenting with configurations. Instead of searching the n8n documentation individually for the right property of a node, the AI assistant can deliver structured answers directly, including example configurations drawn from real workflow templates. This is especially helpful when getting started with more complex integrations or with rarely used community nodes whose documentation would otherwise be harder to find.

Limitations of the server

The MCP server does not replace an understanding of your own business logic and offers no guarantee that a generated workflow will run error-free. Documentation coverage is reportedly high but not complete, and information may be missing or outdated for very new or rarely maintained community nodes. Responsibility for data protection and access rights on the connected n8n instance also remains entirely with the operator; the MCP server itself performs no independent authorization check and simply passes along whatever credentials it has been given.

claude mcp add --transport http n8n <your-n8n-mcp-server-url>

Authentication

OAuth 2.0 (recommended) or API key. OAuth redirects through the n8n login; for self-hosted instances, configure allowed callback URLs.

Required access permissions

Permissions follow the authenticated n8n user. All connected MCP clients see the same enabled workflows; per-client restriction is not supported.

Transmitted or stored data

n8n processes tool calls and returns results. Workflow data is not sent directly to AI model providers; the client controls that.

Security risks

Write tools (workflow creation, editing) allow broad actions; connect only trusted clients. Prompt injection via workflow names is a theoretical risk.

License and costs

License
Sustainable Use License
Cost
free

Community edition is free (self-hosted). n8n Cloud offers paid plans; current pricing at n8n.io/pricing.

Alternatives

Not recorded yet.

At a glance

Provider
n8n
Status
Official server
Deployment
Local and remote
Current version
Not recorded yet.
GitHub stars
210,604
Last reviewed
08.09.2026

Repository and documentation

Categories

Supported clients