Skip to content

MCP Client node#

The MCP Client node is a Model Context Protocol (MCP) client that allows you to use the tools that are exposed by an external MCP server.

You can use the MCP Client node to use MCP tools as regular steps in a workflow.

If you want to use MCP tools as tools for an AI Agent, use the MCP Client Tool node instead.

Credentials

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

Node parameters#

Configure the node with the following parameters.

  • Server Transport: The transport protocol used by the MCP Server endpoint you want to connect to.
  • MCP Endpoint URL: The URL of the external MCP Server. For example, https://mcp.notion.com/mcp.
  • Authentication: The authentication method for authentication to your MCP server. The MCP Client node supports bearer, generic header, and OAuth2 authentication. Select None to attempt to connect without authentication.
  • Tool: Select the tool to use in the node. The list of tools is automatically fetched from the external MCP server.
  • Input Mode:
    • Manual: Specify each tool parameter manually.
    • JSON: Specify tool parameters as a JSON object. Use this mode for tools with nested parameters.

Options#

  • Convert to Binary: Whether to convert images and audio to binary data. If false, images and audio are returned as base64 encoded strings.
  • Timeout: Time in milliseconds to wait for tool calls to finish.

Templates and examples#

Build an MCP Server with Google Calendar and Custom Functions

by Solomon

View template details
Build your own N8N Workflows MCP Server

by Jimleuk

View template details
Build a Personal Assistant with Google Gemini, Gmail and Calendar using MCP

by Aitor | 1Node

View template details
Browse MCP Client integration templates, or search all templates

To use MCP tools with AI Agents, n8n has the MCP Client Tool node.

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.

This page was