MCP Client Tool

The MCP Client Tool node is a Model Context Protocol (MCP) client, allowing you to use the tools exposed by an external MCP server. You can connect the MCP Client Tool node to your models to call external tools with n8n agents.

Credentials

The MCP Client Tool node supports Bearer, generic header, multiple headers, and OAuth2 authentication methods.

Node parameters

Configure the node with the following parameters.

• SSE Endpoint: The SSE endpoint for the MCP server you want to connect to.

• Authentication: The authentication method for authentication to your MCP server. The MCP tool supports bearer, generic header, multiple headers, and OAuth2 authentication. Select None to attempt to connect without authentication.

  • Multiple Headers Auth: Use this when your MCP server requires more than one header, for example an API key and a username. Add each header as a Name and Value pair in the credential. You can add as many headers as you need.

• Tools to Include: Choose which tools you want to expose to the AI Agent:

  • All: Expose all the tools given by the MCP server.

  • Selected: Activates a Tools to Include parameter where you can select the tools you want to expose to the AI Agent.

  • All Except: Activates a Tools to Exclude parameter where you can select the tools you want to avoid sharing with the AI Agent. The AI Agent will have access to all MCP server's tools that aren't selected.

Templates and examples

Browse MCP Client Tool node documentation integration templates or search all templates

Related resources

n8n also has an MCP Server Trigger node that allows you to expose n8n tools to external AI Agents.

Refer to the MCP documentation and MCP specification for more details about the protocol, servers, and clients.

Refer to LangChain's documentation on tools for more information about tools in LangChain.

View n8n's Advanced AI documentation.