MCP Connector

Connect and sync data across SaaS tools

Maton is a remote MCP server and agent toolkit connecting AI agents to 150+ apps (Slack, GitHub, HubSpot, Notion) via OAuth or API key.

Works with hubspotsalesforce

34
Spark score
out of 100
Updated 2 months ago
Source checked Aug 21, 2026
Version 0.1.1
Models
universal

Add to Favorites

Why it matters

Enable seamless integration and data synchronization between multiple SaaS platforms including CRM systems like HubSpot and Salesforce, eliminating manual data entry and ensuring consistent information across your sales and marketing stack.

Outcomes

What it gets done

01

Establish connections to HubSpot for contact and deal management

02

Sync customer data bidirectionally with Salesforce

03

Automate data flow between multiple SaaS applications

04

Maintain real-time consistency across connected tools

Source

Get it from source

Spark does not host a copy of it.

Open source

Reports

Agent outcome reports

No reports yet

Overview

Maton MCP Server

Maton is a remote-hosted MCP server (mcp.maton.ai) plus TypeScript and Python agent toolkits that connect AI agent frameworks to 150+ apps - Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, and more - through one unified API. It supports OAuth and API key authentication, and ships plugins for Claude Code, Cursor, and Codex. Use it when an agent needs to act across many third-party SaaS apps through a single connection instead of integrating each API separately; install via the plugin flow for Claude Code, Cursor, or Codex, or register the server manually for other MCP clients.

What it does

Maton hosts a remote MCP server at https://mcp.maton.ai that connects AI agents to more than 150 apps - Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, and others - through one unified API. Two forms of access exist: OAuth (point an MCP client at the remote server and complete the browser OAuth flow) or an API key (run a local proxy via npx -y @maton/mcp --api-key=YOUR_MATON_API_KEY, authenticated with an Authorization: Bearer header). Alongside the MCP server, the Maton Agent Toolkit exposes the same tool set in each agent framework's native function-calling format: a TypeScript package (@maton/agent-toolkit) for LangChain, the Vercel AI SDK, OpenAI, and MCP, and a Python package (maton-agent-toolkit) for the OpenAI Agents SDK, LangChain, CrewAI, and Strands.

When to use - and when NOT to

Use Maton when an agent needs to reach many different SaaS apps through one authenticated connection rather than wiring up a separate integration per API - for example, an agent that needs to read a Google Sheet, post to Slack, and create a GitHub issue in the same workflow. It fits agent harnesses that already support MCP or one of the supported agent-framework SDKs.

It is not something to reach for when only a single, already-integrated API is needed, or when a client cannot complete an OAuth flow in a browser and does not want to run a local API-key proxy process instead.

How to install

For Claude Code, add the repo as a plugin marketplace and install the plugin:

claude plugin marketplace add maton-ai/agent-toolkit
claude plugin install maton@maton-plugins

Cursor users can add it via /add-plugin and pasting the repo link in the marketplace browser; Codex users run the equivalent codex plugin marketplace add / codex plugin add commands. OpenClaw and other MCP clients can register the server directly - point at https://mcp.maton.ai with streamable-http transport and OAuth, or add it to a .mcp.json / mcp.json config as an http-type MCP server. Each plugin registers the remote server and triggers the OAuth flow in the browser on first use. Manual installers can instead run npm install @maton/agent-toolkit (TypeScript) or uv pip install maton-agent-toolkit (Python). Released under the MIT license.

Who it's for

Teams building AI agents that need to act across many everyday business apps - CRM, docs, chat, and issue tracking among them - through one authenticated connection instead of maintaining a separate integration per API, using whichever MCP client or agent framework they already have in place.

Source 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"
    }
  }
}

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.