mcpField
G
Gbif

Gbif

Remote
pipeworx.ioScience & Education0Updated 3d ago

About Gbif

Gbif is an MCP server for biodiversity researchers, wrapping Global Biodiversity Information Facility API v1. It provides free, unauthenticated queries for species taxonomy and occurrence records.

Key features

  1. 01Search species by common or scientific name
  2. 02Retrieve full taxonomic classification
  3. 03Query georeferenced occurrence records
  4. 04Filter records by country or nearby coordinates

Use cases

  1. 01Verify a species' taxonomic classification
  2. 02Find observation records for a species
  3. 03Survey species recorded near a location

MCP support

It exposes tools for species search, taxonomy, and occurrence queries to MCP clients, including location-based searches. It can connect through the Pipeworx gateway or run as a local stdio MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/gbif/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-gbif

GBIF MCP — wraps the Global Biodiversity Information Facility API v1 (free, no auth)

Part of Pipeworx — an MCP gateway connecting AI agents to 1879+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
search_speciesSearch for species by common or scientific name. Returns matched taxa with rank, classification status, and taxonomic hierarchy. Use get_species with the taxon key for full details.
get_speciesGet complete taxonomic classification for a species (kingdom through subspecies). Requires taxon key from search_species. Returns all ranks and accepted name status.
get_occurrencesGet georeferenced observation records for a species with coordinates, dates, and sources. Pass either name (a scientific name like "Danaus plexippus" — resolved automatically) or a numeric GBIF backbone key. Filter by country code (e.g., 'US', 'BR', 'AU') to narrow results geographically.
occurrences_nearFind species occurrence records NEAR a location (latitude/longitude + radius). PREFER for "what species/wildlife are found near here", "what birds/plants occur around these coordinates", "is recorded near this spot". Optionally filter by a GBIF taxon key (from search_species) to a group or species — e.g. 212 = birds, 6 = plants, 359 = mammals. Returns georeferenced records with species name, date, locality, and source.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "gbif": {
      "url": "https://gateway.pipeworx.io/gbif/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/gbif/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1879+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/search_species \
  -H 'Content-Type: application/json' \
  -d '{"query":"Homo sapiens"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_species. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "gbif": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-gbif"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-gbif

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Gbif data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.