What are the runtime requirements for FirstCycling?
Python 3.10 or higher and the `uv` package manager are required. Dependencies are managed in `pyproject.toml` and include `mcp`, `beautifulsoup4`, `lxml`, `pandas`, and `slumber`.
@r-huijts
Basic information
This is a Model Context Protocol (MCP) server that provides professional cycling data from FirstCycling. It allows you to retrieve information about professional cyclists, race results, and more.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"firstcycling": {
"command": "uv",
"args": [
"--directory",
"/path/to/server/directory",
"run",
"firstcycling.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
FirstCycling is a Model Context Protocol (MCP) server that provides professional cycling data from the FirstCycling website. It allows AI assistants to retrieve comprehensive information about professional cyclists, race results, race details, and historical cycling data through web scraping.
Clone the repository, create a virtual environment with uv venv, install dependencies with uv pip install -e ., then integrate with Claude Desktop by adding a server entry to the Claude config file (claude_desktop_config.json) pointing to the server directory. Tools are invoked via natural language commands through the MCP interface.
Python 3.10 or higher and the `uv` package manager are required. Dependencies are managed in `pyproject.toml` and include `mcp`, `beautifulsoup4`, `lxml`, `pandas`, and `slumber`.
The server uses the FirstCycling API, which fetches data from the FirstCycling website through web scraping.
It provides over 20 MCP tools organized into Rider Information (e.g., `get_rider_info`, `get_rider_grand_tour_results`), Race Information (e.g., `get_race_results`, `get_race_startlist`), and Search Tools (`search_rider`, `search_race`).
Yes. Run `uv run mcp dev firstcycling.py` to start the server and open the MCP Inspector in your browser for testing tools interactively.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Open-source Mac network diagnostics for AI agents and humans. Check connectivity, Wi-Fi, hotspots and traffic from the terminal or MCP.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
Comments