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 descriptionslist_toolkit_functions(toolkit_name, include_methods=True): Lists all functions available in a specific toolkitexecute_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:
- Scanning the Camel framework's toolkit directory
- Analyzing each toolkit class to detect its tools and API requirements
- Creating proper MCP-compatible wrappers for each tool function
- 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:
- Tests are run automatically on pull requests
- 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.
Metadata
Release files for camel-toolkits-mcp 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| camel_toolkits_mcp-0.1.3.tar.gz | 13.1 kB | Without provenance | Details for camel_toolkits_mcp-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| camel_toolkits_mcp-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for camel_toolkits_mcp-0.1.3-py3-none-any.whl |
Total release size: 23.2 kB
Release files / camel_toolkits_mcp-0.1.3.tar.gz
| Download URL | camel_toolkits_mcp-0.1.3.tar.gz |
|---|---|
| Size | 13.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0ecc58c64fe663d5cd565a1a7535dcab4530eac1478d0d4b130ba64ae3f40250
|
|
BLAKE2b-256 checksum How to use checksums |
e6f0d30dfa48a8199f0a7908c594931ba10047022cfc7c4d1a8c5aafcd4904d3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Release files / camel_toolkits_mcp-0.1.3-py3-none-any.whl
| Download URL | camel_toolkits_mcp-0.1.3-py3-none-any.whl |
|---|---|
| Size | 10.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f96f5af12c0ad5dc9fa25231735099f417422dcf043c34dd4ac0b52cb19061c7
|
|
BLAKE2b-256 checksum How to use checksums |
0e5f19c3235c0a918a6032788d8b4df785f9353d862d15cd655f701ffc83550c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Security for camel-toolkits-mcp 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.