Exposes BirdNet-Pi data and functionality through a Model Context Protocol (MCP) server.
If you already use BirdNet, the birdnet mcp server is the piece that lets your assistant work with it directly. Exposes BirdNet-Pi data and functionality through a Model Context Protocol (MCP) server.
A Model Context Protocol (MCP) server for BirdNET-Pi integration. Provides tools to query bird detection data, statistics, audio recordings, activity patterns, and reports from a local BirdNET-Pi installation.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
get_detections — Get bird detections filtered by date range and optional species. - start_date (required): Start date in YYYY-MM-DD format - end_date (required): Endget_stats — Get aggregate detection statistics for a time period. - period (required): day, week, month, or all - min_confidence (optional): Minimum confidenceget_audio — Retrieve the audio recording for a specific bird detection. - filename (required): Audio filename from a detection record - format (optional): base64get_activity — Get hourly bird activity patterns for a specific day. - date (required): Date in YYYY-MM-DD format - species (optional): Species name filtergenerate_report — Generate a detection report for a date range. - start_date (required): Report start date - end_date (required): Report end date - format (optional)Configuration is passed through the environment: MCP_HTTP_HOST. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. BirdNet's toolset — get_detections, get_stats, get_audio and 2 more — is a fair guide to whether it matches your workflow. It is maintained by DMontgomery40; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against BirdNet's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| get_detections | Get bird detections filtered by date range and optional species. - start_date (required): Start date in YYYY-MM-DD format - end_date (required): End date in YYYY-MM-DD format - species (optional): Species name filter (pa |
| get_stats | Get aggregate detection statistics for a time period. - period (required): day, week, month, or all - min_confidence (optional): Minimum confidence threshold 0.0-1.0 (default: 0.0) |
| get_audio | Retrieve the audio recording for a specific bird detection. - filename (required): Audio filename from a detection record - format (optional): base64 (default) or buffer |
| get_activity | Get hourly bird activity patterns for a specific day. - date (required): Date in YYYY-MM-DD format - species (optional): Species name filter |
| generate_report | Generate a detection report for a date range. - start_date (required): Report start date - end_date (required): Report end date - format (optional): json (default) or html |
{
"mcpServers": {
"birdnet": {
"command": "python",
"args": ["/absolute/path/to/mcp-BirdNET-Pi-server/server.py"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| MCP_HTTP_HOST | Endpoint or connection string the server talks to. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.