Gbif MCP Server

Search GBIF species taxonomy, occurrence records, datasets, and publishers.

Remote serverstreamable-http

What is the Gbif MCP server?

If you already use Gbif, the gbif mcp server is the piece that lets your assistant work with it directly. Search GBIF species taxonomy, occurrence records, datasets, and publishers.

What the server does

  • Declarative tool definitions — single file per tool, framework handles registration and validation
  • Unified error handling across all tools
  • Pluggable auth (none, jwt, oauth)
  • Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
  • Structured logging with optional OpenTelemetry tracing
  • Runs locally (stdio/HTTP) or on Cloudflare Workers from the same codebase

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • gbif_match_species — Match a species name against the GBIF backbone taxonomy — returns taxonKey, confidence score, and full classification
  • gbif_bulk_match_species — Match up to 50 scientific names to backbone taxon keys in one call — results in input order, per-name NONE/ERROR isolation
  • gbif_get_species — Fetch a single backbone taxon by key — full classification, authorship, synonymy, vernacular name, descendant count
  • gbif_search_species — Search or browse the GBIF backbone taxonomy by name fragment, rank, kingdom, family, or genus
  • gbif_get_species_classification — Return the root-to-parent classification chain for a taxon — root-first ordered array from kingdom to the queried taxon's immediate parent (the taxon
  • gbif_get_species_children — List direct children of a backbone taxon — genera within a family, species within a genus
  • gbif_search_occurrences — Search 2.4B+ GBIF occurrence records with Darwin Core filters — country, bounding box, WKT geometry, year, month, basis of record
  • gbif_count_occurrences — Count occurrences matching a filter without fetching records — fast single-number response
  • gbif_get_occurrence — Fetch a single occurrence record by key — full Darwin Core record with GADM geography, media, and quality flags
  • gbif_occurrence_facets — Aggregate occurrence counts by a dimension — country, year, basis of record, dataset, kingdom, and more
  • gbif_search_datasets — Search GBIF datasets by keyword, type, country, or publishing organization
  • gbif_get_dataset — Fetch full dataset metadata by UUID — title, description, citation, contacts, license, DOI, coverage

Installation

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.

Credentials and setup notes

Configuration is passed through the environment: MCP_TRANSPORT_TYPE, MCP_LOG_LEVEL, DATASET_KEY, KINGDOM_KEY, PHYLUM_KEY, CLASS_KEY, ORDER_KEY, FAMILY_KEY. 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.

Where it fits

Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Gbif's toolset — gbif_match_species, gbif_bulk_match_species, gbif_get_species and 11 more — is a fair guide to whether it matches your workflow. It is maintained by cyanheads; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Gbif.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
gbif_match_speciesMatch a species name against the GBIF backbone taxonomy — returns taxonKey, confidence score, and full classification
gbif_bulk_match_speciesMatch up to 50 scientific names to backbone taxon keys in one call — results in input order, per-name NONE/ERROR isolation
gbif_get_speciesFetch a single backbone taxon by key — full classification, authorship, synonymy, vernacular name, descendant count
gbif_search_speciesSearch or browse the GBIF backbone taxonomy by name fragment, rank, kingdom, family, or genus
gbif_get_species_classificationReturn the root-to-parent classification chain for a taxon — root-first ordered array from kingdom to the queried taxon's immediate parent (the taxon itself is not included)
gbif_get_species_childrenList direct children of a backbone taxon — genera within a family, species within a genus
gbif_search_occurrencesSearch 2.4B+ GBIF occurrence records with Darwin Core filters — country, bounding box, WKT geometry, year, month, basis of record
gbif_count_occurrencesCount occurrences matching a filter without fetching records — fast single-number response
gbif_get_occurrenceFetch a single occurrence record by key — full Darwin Core record with GADM geography, media, and quality flags
gbif_occurrence_facetsAggregate occurrence counts by a dimension — country, year, basis of record, dataset, kingdom, and more
gbif_search_datasetsSearch GBIF datasets by keyword, type, country, or publishing organization
gbif_get_datasetFetch full dataset metadata by UUID — title, description, citation, contacts, license, DOI, coverage
gbif_search_publishersSearch GBIF-registered publishing organizations by name fragment or country
PrerequisitesThe Prerequisites tool exposed by this server.

How to install the Gbif MCP server

{
  "mcpServers": {
    "gbif-biodiversity-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/gbif-biodiversity-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
MCP_TRANSPORT_TYPEConfiguration value read at startup.Optional
MCP_LOG_LEVELConfiguration value read at startup.Optional
DATASET_KEYCredential the server authenticates with.Yes
KINGDOM_KEYCredential the server authenticates with.Yes
PHYLUM_KEYCredential the server authenticates with.Yes
CLASS_KEYCredential the server authenticates with.Yes
ORDER_KEYCredential the server authenticates with.Yes
FAMILY_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Gbif to gbif match species.
  • Use Gbif to gbif bulk match species.
  • Use Gbif to gbif get species.

Frequently asked questions

It connects Gbif to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (gbif_match_species, gbif_bulk_match_species, gbif_get_species, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Gbif directly.