Skip to main content
Glama
jbeker

birdnet-mcp

by jbeker
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
BIRDNET_GO_URLYesBase URL of the BirdNET-Go instance, e.g. http://birdnet.local:8080
BIRDNET_GO_TIMEOUTNoHTTP timeout in seconds (default 10)10

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_recent_detectionsA

Get the most recent bird detections ("what's been heard lately?").

Args:
    limit: Number of detections to return (1-50, default 15).
get_detectionsA

Get bird detections for a specific day, optionally narrowed to an hour window or species.

Args:
    date: Day to query, YYYY-MM-DD (default: today in the MCP server's local timezone).
    hour: Starting hour 0-23 to narrow to an hourly window (optional).
    duration: Window length in hours 1-24 when hour is set (default 1).
    species: Filter to a species (common or scientific name, optional).
    limit: Max detections to return (1-100, default 25).
    offset: Pagination offset (default 0).
search_detectionsA

Search historical detections with flexible filters. Results are paginated 20 per page.

Args:
    species: Species filter (common or scientific name; empty = all species).
    date_start: Earliest date, YYYY-MM-DD (empty = no lower bound).
    date_end: Latest date, YYYY-MM-DD (empty = no upper bound).
    confidence_min: Minimum confidence 0.0-1.0.
    confidence_max: Maximum confidence 0.0-1.0.
    verified_status: One of: any, correct, unverified, falsePositive.
    time_of_day: One of: any, day, night, sunrise, sunset.
    page: 1-based page number.
    sort_by: One of: date_desc, date_asc, species_asc, species_desc, confidence_desc.
get_detectionA

Get full details for a single detection, including weather context if recorded.

Args:
    detection_id: The detection's numeric id.
    include_media_urls: Include URLs for the audio clip and spectrogram (URLs only, not bytes).
get_species_summaryA

Per-species statistics: detection counts, first/last heard, average confidence.

Args:
    start_date: Earliest date, YYYY-MM-DD (optional; omit for all time).
    end_date: Latest date, YYYY-MM-DD (optional).
    limit: Max species to return (1-200, default 50), ordered by detection count.
get_new_speciesA

Species detected for the first time ever within the recent period ("anything new lately?").

Args:
    days: Look-back window in days (default 30).
    limit: Max species to return (1-100, default 25).
get_activity_patternA

Temporal detection activity: counts per day over a date range, or per hour for one day.

Analytics are calendar-day granularity; hourly data is available per single day only.

Args:
    granularity: "daily" (counts per day over start_date..end_date) or
        "hourly" (24 hourly counts; requires date and species).
    species: Species name (required for hourly, optional filter for daily).
    date: Day for hourly granularity, YYYY-MM-DD.
    start_date: Range start for daily granularity, YYYY-MM-DD.
    end_date: Range end for daily granularity, YYYY-MM-DD.
get_instance_statusA

Check whether the BirdNET-Go instance is reachable and report its health.

get_species_infoA

Species details (rarity for this location) and taxonomy for a scientific name.

Args:
    scientific_name: Full scientific name including genus and species,
        e.g. "Cardinalis cardinalis".

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 9 tools

Disambiguation4/5

The detection-fetching tools (get_recent_detections, get_detections, search_detections) overlap somewhat, but their scopes are clearly separated by time window, filters, and pagination. Species statistics, new species, activity patterns, status, and taxonomy tools are all distinct.

Naming Consistency5/5

All tools use lowercase snake_case with a consistent get_/search_ verb prefix followed by a clear noun. Singular and plural forms like get_detection and get_detections are predictable, and search_detections fits the same pattern.

Tool Count5/5

Nine tools cover the server's read-only bird-detection analytics scope without redundancy. Each tool contributes a distinct query type, and the count fits comfortably within a well-scoped tool set.

Completeness5/5

The surface covers recent detections, single-detection detail, day/hour filtering, flexible historical search, species summaries, new species discovery, temporal activity, taxonomy, and instance health. For a read-only monitoring and analytics server, no significant workflow dead ends are apparent.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources