DMontgomery40 MCP Local Server

Provides BirdNet-Pi detections, audio access, stats, and reports via a local MCP server.

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-dmontgomery40_mcp-local-server": {
      "command": "python",
      "args": [
        "server.py"
      ],
      "env": {
        "BIRDNET_AUDIO_DIR": "data/audio",
        "BIRDNET_REPORT_DIR": "data/reports",
        "BIRDNET_DETECTIONS_FILE": "data/detections.json"
      }
    }
  }
}

This BirdNet-Pi MCP Server exposes bird detections, audio access, statistics, and reports via a minimal, locally runnable MCP endpoint. It lets you query detections by date and species, retrieve audio, view daily activity, and generate reports from BirdNet-Pi data using a simple local MCP client.

How to use

You connect to the MCP server from your client to access bird detections, statistics, audio, and reports. Use the available functions to filter detections by date range and species, fetch audio recordings for specific detections, review daily activity patterns, and generate reports for a chosen time span. All interactions occur through standard MCP function invocations via the local server endpoint.

How to install

# Step 1: Clone the repository
git clone https://github.com/YourUsername/mcp-server.git
cd mcp-server

# Step 2: Create and activate a virtual environment
python -m venv venv
source venv/bin/activate  # On Windows use: venv\Scripts\activate

# Step 3: Install dependencies
pip install -r requirements.txt

# Step 4: Set up your data directories
mkdir -p data/audio data/reports

# Step 5: Run the MCP server
python server.py

Configuration and runtime details

The server uses environment variables to locate data and store outputs. You set these variables to point to your data locations before starting the server.

# Environment variables you can configure
export BIRDNET_DETECTIONS_FILE=data/detections.json
export BIRDNET_AUDIO_DIR=data/audio
export BIRDNET_REPORT_DIR=data/reports

Other important notes

The MCP server runs locally and serves on http://localhost:8000 by default when started with the standard Python entry.
You can adjust where detections, audio, and reports are stored by changing the corresponding environment variables before launching the server.
When you’re ready to stop, terminate the process running python server.py.

Available tools

getBirdDetections

Retrieve detections filtered by date range and optional species to support targeted bird monitoring.

getDetectionStats

Return statistics for detections over a chosen period such as day, week, month, or all time, with optional confidence filtering.

getAudioRecording

Provide access to the audio file for a specific detection, returned as base64 or binary buffer.

getDailyActivity

Show bird activity patterns for a specified day, optionally filtered by species.

generateDetectionReport

Create a report of detections for a given date range in formats like html or json.

Built by

VeilStrat

AI signals for GTM teams