A collection of FastMCP servers for various APIs.
FastMCP Server Collection provides a set of ready-to-use FastMCP servers that allow you to interact with various APIs through the Model Control Protocol (MCP). This makes it easy to integrate external services into MCP-based workflows.
- Python 3.11
- uv
# Clone the repository
git clone https://github.com/TaylorFinklea/fastmcp-server-collection.git
cd fastmcp-server-collection
# Create a virtual environment
uv venv --python 3.11
source .venv/bin/activate
# Install with uv
uv pip install -e .
# Create a .env file
cp .env.example .env
FastMCP Server Collection provides servers for different APIs. See FastMCP CLI documentation for more information.
You can run a specific server using:
fastmcp run servers/<server_name>.py:mcp --transport streamable-http # possible values: stdio, streamable-http, sse
For example, to run the Skyvern server as a streamable http server:
fastmcp run servers/skyvern.py:mcp --transport streamable-http
fastmcp install servers/<server_name>.py:mcp --env-file .env
For example, to install the Skyvern server:
# open Claude Desktop > go to Settings > Developer > Edit Config
# saves to /Users/YOURUSER/Library/Application Support/Claude on macOS
fastmcp install servers/skyvern.py:mcp --env-file .env
A server for interacting with the Skyvern API. This server requires a Skyvern API key, which should be set in your environment variables or in a .env
file in the project root.
Required environment variables:
SKYVERN_API_KEY
: Your Skyvern API keySKYVERN_URL
: The base URL for the Skyvern API
- Create a new Python file in the
fastmcp_server_collection/servers/
directory. See FastMCP Server documentation for more information. - Implement the necessary functionality using FastMCP
- Ensure your file includes code that starts the FastMCP server when run directly
- Update the server registry in the README to include your new server
🚧 Work in Progress: The testing framework is currently under development. 🚧
REST2MCP uses pytest for testing. The tests are located in the tests/
directory.
To run the tests, first install the test dependencies:
# Install with test dependencies
uv pip install -e ".[test]"
Then run the tests:
# Run all tests
pytest
# Run tests with verbose output
pytest -v
# Run tests with coverage report
pytest --cov=fastmcp_server_collection
This project uses GitHub Actions for continuous integration. The workflow is defined in .github/workflows/ci.yml
.
The CI pipeline:
- Runs on Python 3.11
- Checks code formatting with Black
- Runs tests with coverage reporting
- Uploads coverage reports to Codecov
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.