mcpField
M
Maton MCP Server

Maton MCP Server

Local
github.com/maton-aiAI & Agents50Updated 4w ago
Repository

About Maton MCP Server

Maton Agent Toolkit connects AI agents to Maton's hosted remote MCP server, which covers over 150 apps through one API. It suits developers who want agents to reach tools such as Google Workspace, GitHub and Slack. The repo offers TypeScript and Python toolkits and plugins for several agent harnesses.

Key features

  1. 01Hosted remote MCP server with OAuth or API key
  2. 02Local proxy started through npx
  3. 03TypeScript and Python agent toolkits
  4. 04Plugins for Claude Code, Cursor and Codex
  5. 05Access to over 150 connected apps

Use cases

  1. 01Letting AI agents work with HubSpot or Salesforce data
  2. 02Installing the Maton plugin in Claude Code or Cursor
  3. 03Calling Maton tools from LangChain or CrewAI

MCP support

Maton hosts a remote MCP server at https://mcp.maton.ai that exposes app tools to MCP clients. The agent toolkits discover these tools and convert them into each framework's function-calling format.

#modelcontextprotocol#agent-toolkit#api-integration

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "agent-toolkit-maton-ai": {
      "command": "npx",
      "args": [
        "-y",
        "@maton/mcp"
      ]
    }
  }
}
Run commandnpx -y @maton/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@maton/mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Maton Agent Toolkit

This repo helps you connect AI agents to Maton, which allows you to connect and automate 150+ apps (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, and more) through a unified API.

Model Context Protocol (MCP)

Maton hosts a remote MCP server at https://mcp.maton.ai. It supports both OAuth and API key (Authorization: Bearer header) authentication, so you can connect securely from any MCP client.

  • Remote (OAuth): point your MCP client at https://mcp.maton.ai and complete the OAuth flow in the browser.
  • Local (API key): run the local proxy with npx -y @maton/mcp --api-key=YOUR_MATON_API_KEY.

See the MCP package for setup instructions, Docker usage, and the full list of tools.

Agent Toolkit

The Maton Agent Toolkit connects popular agent frameworks to the Maton MCP server through function calling. It discovers the tools available on https://mcp.maton.ai and exposes them in each framework's native format.

npm install @maton/agent-toolkit      # TypeScript
uv pip install maton-agent-toolkit    # Python

Plugins

We ship plugins for popular agent harnesses that wire up the Maton MCP server for you. Each plugin registers the remote server at https://mcp.maton.ai, so once installed the Maton tools are available and you complete the OAuth flow in your browser on first use.

Claude Code

Add this repo as a plugin marketplace, then install the Maton plugin:

claude plugin marketplace add maton-ai/agent-toolkit
claude plugin install maton@maton-plugins
Cursor
  1. Run /add-plugin.
  2. Click Browse marketplace.
  3. Paste the repo link: https://github.com/maton-ai/agent-toolkit.
  4. Install the plugin.
Codex

Add this repo as a plugin marketplace, then install the Maton plugin:

codex plugin marketplace add maton-ai/agent-toolkit
codex plugin add maton@maton-plugins
OpenClaw

Register the Maton MCP server in your openclaw.json under mcp.servers, then authenticate via OAuth in the browser on first use:

{
  "mcp": {
    "servers": {
      "maton": {
        "url": "https://mcp.maton.ai",
        "transport": "streamable-http",
        "auth": "oauth"
      }
    }
  }
}

Manual installation

If you'd rather not use a plugin, register the Maton MCP server directly in your MCP client config (.mcp.json for Claude Code, mcp.json for Cursor):

{
  "mcpServers": {
    "maton": {
      "type": "http",
      "url": "https://mcp.maton.ai"
    }
  }
}

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.