Skip to content
MCP server

Chanty

MCP server that connects AI clients to the Chanty team chat API over stdio

Runs locally
Install
Pricing
Open source
Platforms
CLI, API, self-hosted
Runs
Locally
Version
0.1.0
Listing updated
today

Similar MCP servers

About Chanty

Chanty is an open-source MCP server for agent tooling. It runs locally on your machine and is started by your AI client.

The README says this is a Model Context Protocol server for connecting Chanty, a team communication platform, to GenAI applications. It runs over stdio and is installed from PyPI as chanty-mcp-server, or from source with pip.

Authentication uses a Chanty API key supplied through the CHANTY_API_KEY environment variable, with an optional CHANTY_API_URL for the endpoint. The README mentions multiple authentication methods, rate limiting, retry handling and async support, but does not list the individual tools it exposes.

It suits developers who want an AI assistant to interact with Chanty workspaces programmatically. The project is MIT licensed.

Install

Run in a terminal

claude mcp add chanty-mcp-server --env CHANTY_API_KEY='<CHANTY_API_KEY>' -- uvx chanty-mcp-server

Add to claude_desktop_config.json

{
  "mcpServers": {
    "chanty-mcp-server": {
      "command": "uvx",
      "args": [
        "chanty-mcp-server"
      ],
      "env": {
        "CHANTY_API_KEY": "<CHANTY_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "chanty-mcp-server": {
      "command": "uvx",
      "args": [
        "chanty-mcp-server"
      ],
      "env": {
        "CHANTY_API_KEY": "<CHANTY_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "chanty-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "chanty-mcp-server"
      ],
      "env": {
        "CHANTY_API_KEY": "<CHANTY_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "chanty-mcp-server": {
      "command": "uvx",
      "args": [
        "chanty-mcp-server"
      ],
      "env": {
        "CHANTY_API_KEY": "<CHANTY_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "chanty-mcp-server": {
      "command": "uvx",
      "args": [
        "chanty-mcp-server"
      ],
      "env": {
        "CHANTY_API_KEY": "<CHANTY_API_KEY>"
      }
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Configuration

  • CHANTY_API_KEYAPI Key for CHANTYRequired
  • CHANTY_API_URLAPI URL for CHANTY

What it does

Stdio transport
Runs as a local process that MCP clients launch over standard input and output.
API key authentication
Reads the Chanty API key and optional endpoint URL from environment variables.
Rate limiting
The README says the server includes rate limiting for Chanty API calls.
Retry and error handling
The README describes built-in error handling and retry logic.
Async support
The README mentions asynchronous operation for better performance.

Good for

  • Letting an AI assistant read or post messages in Chanty channels
  • Automating routine team communication from a GenAI workflow
  • Connecting Chanty data to an MCP-compatible AI client

Pricing

Open source

Free and MIT licensed; Chanty's own service pricing is separate.

Chanty FAQ

How is the server installed?

The README gives pip install chanty-mcp-server, or cloning the repository and running pip install -e .

What credentials does it need?

A Chanty API key set as CHANTY_API_KEY is required; CHANTY_API_URL is an optional environment variable.

What license does it use?

The README states the project is released under the MIT License.

Is Chanty free?

Yes. Chanty is open source, so you can use and self-host it for free.

How do I add Chanty to Claude Code?

Run this command in your terminal: claude mcp add chanty-mcp-server --env CHANTY_API_KEY='<CHANTY_API_KEY>' -- uvx chanty-mcp-server

What are the best alternatives to Chanty?

The closest alternatives to Chanty are toolhive, mcp-gateway-registry, Hive Connector, Synapbus and Z-Image MCP.

Where this comes from

  • Description: written from the project's README and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers