ebird

This MCP server exposes eBird data through Claude’s chat interface. It connects to the eBird API using your API key and serves birding data through natural language prompts. You can ask the model to fetch recent observations, checklists, hotspots, and taxonomy data, and the model will call the MCP server when appropriate to retrieve up-to-date birding information. Use the example prompts to understand the kinds of queries you can make, or ask for more specific filters (locations, dates, species) and the server will return structured results that you can read in the chat.

Through this server you get access to:

• Observations: recent sightings by location or by species, including notable/rare records.
• Checklists: recent or specific-date checklists, top contributors, and detailed checklist information.
• Hotspots: hotspots by location and nearby hotspots relative to a given point.
• Taxonomy: official taxonomy data and subspecies lists for species in eBird.
• Response control: the AI can decide when to call the eBird MCP Server, or you can explicitly instruct it to query, depending on your prompt’s intent.

Prerequisites:

• Python 3.8+ installed on your system
• An eBird API key
• Access to a terminal/command prompt

1. Clone the repository

git clone git@github.com:siansiansu/ebird-mcp-server.git
cd ebird-mcp-server

2. Create and activate a virtual environment (recommended)

python -m venv venv
# on Windows
venv\Scripts\activate
# on macOS/Linux
source venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Configure your eBird API key in the MCP configuration (see the example below). Ensure the server script path is correct for your environment.

5. Run the server

python server.py

6. Point Claude to the MCP server by updating claude_desktop_config.json as shown in the README, replacing paths and adding your EBIRD_API_KEY.

Tips and caveats:

• Ensure your EBIRD_API_KEY is kept secret and not shared in public configs.
• The MCP server expects the Python executable path and the absolute path to server.py as shown in the configuration example.
• If you encounter API rate limits or authentication errors, verify your API key and review eBird’s API usage terms.
• You can extend prompts by specifying location, date ranges, or species name; the server will translate these into eBird API requests.
• If Claude cannot reach the MCP server, verify that the server is running, the paths are correct, and the EBIRD_API_KEY environment variable is set in the running process.