Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

coze-mcp-server

MCP.Pizza Chef: coze-dev

The coze-mcp-server is a Model Context Protocol server that exposes Coze platform resources and tools. It enables management of workspaces, bots, and voices through a variety of API endpoints, supporting bot creation, updates, publishing, and chat interactions. Designed for seamless integration, it facilitates real-time context sharing and interaction with Coze's AI-driven workflows and voice capabilities.

Use This MCP server To

List and manage Coze workspaces programmatically Create, update, and publish bots via MCP interface Retrieve detailed bot information for automation Engage in chat sessions with bots or workflows List available voices for voice-enabled applications

README

COZE MCP Server

A Model Context Protocol server that provides coze resource and tool.

Available Tools

  • list_workspaces - Get workspaces list
  • list_bots - Get bots list
  • create_bot - Create bot
  • get_me: Get self user info
  • list_workspaces: List workspaces
  • list_bots: List bots
  • retrieve_bot: Retrieve bot info
  • create_bot: Create bot
  • update_bot: Update bot
  • publish_bot: Publish bot to API channel
  • chat_with_bot: Chat with bot
  • chat_with_workflow: Chat with workflow
  • list_voices: List voice

Installation

Using uv (recommended)

When using uv no specific installation is needed. We will use uvx to directly run coze-mcp-server.

Using PIP

Alternatively you can install coze-mcp-server via pip:

pip install coze-mcp-server

After installation, you can run it as a script using:

python -m coze_mcp_server

Configuration

Configure for Claude.app

Add to your Claude settings:

Using uvx
"mcpServers": {
  "coze-mcp-server": {
    "command": "uvx",
    "args": ["coze-mcp-server"]
  }
}
Using docker
"mcpServers": {
  "coze-mcp-server": {
    "command": "docker",
    "args": ["run", "-i", "--rm", "ghcr.io/coze-dev/coze-mcp-server"]
  }
}
Using pip installation
"mcpServers": {
  "coze-mcp-server": {
    "command": "python",
    "args": ["-m", "coze_mcp_server"]
  }
}

Configure for Zed

Add to your Zed settings.json:

Using uvx
"context_servers": [
  "coze-mcp-server": {
    "command": "uvx",
    "args": ["coze-mcp-server"]
  }
],
Using pip installation
"context_servers": {
  "coze-mcp-server": {
    "command": "python",
    "args": ["-m", "coze_mcp_server"]
  }
},

License

MIT License.

coze-mcp-server FAQ

How do I install the coze-mcp-server?
You can install it via pip using 'pip install coze-mcp-server' or run it directly with uvx without installation.
What tools does coze-mcp-server provide?
It provides tools for listing workspaces, managing bots (create, update, publish), chatting with bots or workflows, and listing voices.
Can I use coze-mcp-server to interact with AI workflows?
Yes, it supports chatting with workflows, enabling real-time AI-driven interactions.
How do I run the coze-mcp-server after installation?
Run it as a script using 'python -m coze_mcp_server' or use uvx for direct execution.
Is coze-mcp-server compatible with multiple LLM providers?
While it primarily integrates with Coze, it can be used alongside models from OpenAI, Claude, and Gemini through MCP clients.
What is the purpose of the 'publish_bot' tool?
It publishes a bot to an API channel, making it accessible for external applications.
How can I retrieve user information using coze-mcp-server?
Use the 'get_me' tool to get self user info securely.
Does coze-mcp-server support voice features?
Yes, it includes a tool to list available voices for voice-enabled AI applications.