What is Camel Toolkits Mcp

camel-toolkits-mcp is a lightweight server that exports CAMEL framework toolkits as MCP-compatible tools, bridging the gap between the CAMEL AI framework’s toolkit ecosystem and MCP-compatible clients.

Use cases

Use cases include integrating CAMEL toolkits into AI applications, dynamically loading different toolkits based on user needs, and exposing toolkit functions as MCP-compatible services for enhanced interoperability.

How to use

You can install camel-toolkits-mcp directly from PyPI using ‘pip install camel-toolkits-mcp’, or clone the repository from GitHub and install it locally. Configure it with MCP clients like uvx by specifying the server command and necessary environment variables.

Key features

Key features include dynamic discovery and listing of available CAMEL toolkits, runtime loading and execution of toolkit functions, and seamless conversion of CAMEL toolkit functions to MCP-compatible tools.

Where to use

camel-toolkits-mcp can be used in various fields such as AI development, machine learning applications, and any LLM-based applications that require dynamic toolkit integration.

CAMEL Toolkits MCP

A lightweight server that exports CAMEL framework toolkits as MCP-compatible tools.

Overview

This project bridges the gap between the CAMEL AI framework’s toolkit ecosystem and MCP (Model Control Protocol) compatible clients. It allows you to dynamically load and expose any Camel toolkit as an MCP server, making these tools available to a wide range of LLM-based applications.

Key features:

• Dynamically discover and list available CAMEL toolkits
• Load and execute toolkit functions at runtime
• Seamless conversion of CAMEL toolkit functions to MCP-compatible tools

Installation

You can install the package directly from PyPI:

pip install camel-toolkits-mcp

Or install from source:

git clone https://github.com/jinx0a/camel-toolkits-mcp.git
cd camel-toolkits-mcp
pip install -e .

Config with MCP clients

Using with uvx

You can easily configure uvx to run the CAMEL toolkits server like this:

{
  "mcpServers": {
    "camel-toolkits": {
      "command": "uvx",
      "args": [
        "camel-toolkits-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "your-openai-key",
        "NOTION_TOKEN": "your-notion-token",
        "...": "..."
      }
    }
  }
}

Local Development Configuration

If you’re developing this package locally, you can configure UVX to use your development version:

{
  "mcpServers": {
    "camel_toolkits_mcp": {
      "command": "/path/to/python",
      "args": [
        "/path/to/camel_toolkits_mcp/server.py"
      ],
      "env": {
        "OPENAI_API_KEY": "your-openai-key",
        "NOTION_TOKEN": "your-notion-token",
        "...": "..."
      }
    }
  }
}

Available Tools

The server exposes the following MCP-compatible tools:

• get_toolkits_list(): Lists all available CAMEL toolkits with their descriptions
• list_toolkit_functions(toolkit_name, include_methods=True): Lists all functions available in a specific toolkit
• execute_toolkit_function(toolkit_name, function_name, toolkit_params=None, function_args=None): Executes a specific function from a toolkit

Example: Using Tools

# First, discover available toolkits
toolkits = get_toolkits_list()
print(toolkits)  # Shows all available toolkits

# List functions in a specific toolkit (e.g., NotionToolkit)
functions = list_toolkit_functions(toolkit_name="NotionToolkit")

# Execute a toolkit function
result = execute_toolkit_function(
    toolkit_name="NotionToolkit",
    function_name="search_pages",
    toolkit_params={"notion_token": "your-notion-token"},
    function_args={"query": "meeting notes"}
)

Architecture

The router works by:

1. Scanning the CAMEL framework’s toolkit directory
2. Analyzing each toolkit class to detect its tools and API requirements
3. Creating proper MCP-compatible wrappers for each tool function
4. Exposing these functions through the FastMCP server

Supported Toolkits

This server supports all toolkits in the CAMEL framework, including:

• NotionToolkit
• OpenAIToolkit
• WebSearchToolkit
• And many more…

API Key Management

For toolkits requiring API keys (like Notion, OpenAI, etc.), you should provide them in the environment variables when configuring the MCP server.

Development

To set up a development environment:

pip install -e ".[dev]"

Run tests:

pytest

Contributing

Contributions are welcome! The project uses GitHub Actions for CI/CD:

1. Tests are run automatically on pull requests
2. New releases are automatically published to PyPI when a GitHub release is created

License

This project is licensed under the MIT License - see the LICENSE file for details.