Overview

iNaturalist's index of 380M+ georeferenced citizen-science observations of plants, animals, and fungi. Search sightings by area, date, taxon, and annotation; read the community identification thread behind a record; chart when a taxon appears in a place; rank the species of an area; and check what a look-alike is most often confused with. Keyless and read-only, running as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.

Composes with servers covering institutional specimen records, botanical nomenclature, and geocoding — this one contributes the observation, identification-thread, and phenology layer.

Tools

Resources

Both resources mirror data also reachable through inaturalist_get_taxon and inaturalist_get_observation — useful for clients that don't surface MCP resources.

Capability reference

inaturalist_list_reference _tool

• topic selects one table: controlled_terms, quality_grades, licenses, ranks, iconic_taxa, conservation_status_codes; source reports whether it came from iNaturalist or the published spec
• taxon_id applies only to controlled_terms and adds observed_usage — which annotation pairs identifiers have actually recorded for that taxon, with counts. Each row carries term_id and term_value_id, ready to pass to the annotation filters; labels repeat across attributes ("Egg" is both a Life Stage and an Evidence of Presence value), so filter by the ids
• Every other tool's recovery hint routes here: an unrecognised filter value is not rejected upstream, it silently returns nothing

inaturalist_resolve_name _tool

• type: taxon (name-prefix autocomplete) or place / project / user / any (scored cross-kind search); rank narrows taxa only; limit 1–30 (default 10), applied in-process on every type
• Taxon lookup matches a name prefix, not words inside a name — "monarch" hits where "monarch butterfly" misses
• A miss is a result: found: false with guidance naming why, rather than an error
• Each candidate carries kind and id — the identifier every other tool takes. A user candidate also carries login, the value leaderboard entries and an observation's observer relay; its name is the display name

inaturalist_find_places _tool

• Exactly one of q (place-name prefix) or all four of nelat, nelng, swlat, swlng; neither or both fails as invalid_geography, as does a box with nelat south of swlat. A blank q reads as unset, and nelng west of swlng is an antimeridian-crossing box, not an error
• q returns places[]; the bounding box returns standard[] and community[] as separate lists
• Each place carries bbox, place_type, admin_level, ancestor_place_ids, location, and slug; boundary polygons are stripped, since one upstream response carries 247 KB of them
• per_page (1–30, default 10) binds the bounding-box arm only, where it bounds standard[] and community[] separately, so cap is per_page × 2. The name-prefix endpoint publishes no page size, and its fixed page is disclosed through the truncation enrichment

inaturalist_search_observations _tool

• An area is given in exactly one form — place_id, the lat+lng+radius triple in kilometres (0 < radius ≤ 500), or the four-corner bounding box with nelat at or north of swlat; partial, mixed, a zero radius, or an inverted box fails as invalid_geography
• Filters: taxon_id, d1/d2, quality_grade, captive, term_id+term_value_id, iconic_taxa, hrank/lrank, csi, threatened/native/introduced/endemic, user_id or user_login, project_id, licensed/photo_licensed, license/photo_license, and q+search_on
• user_id, user_login, and project_id come from inaturalist_resolve_name (a login also rides leaderboard entries and every observation's observer). Passing both observer forms fails as conflicting_observer; an unknown observer or project fails as unknown_user or unknown_project_id
• license and photo_license take licence codes — cc0, cc-by, cc-by-nc, cc-by-nd, cc-by-sa, cc-by-nc-nd, cc-by-nc-sa, any case — joined as OR, so ["cc-by","cc0"] finds sightings reusable with attribution only. photo_license matches a record with any photo under the code, independently of the record's own licence. licensed/photo_licensed only test for a non-null licence
• Ordered pairs are checked before the request: d1 after d2 fails as inverted_date_range (on every tool that takes dates), and an hrank finer than lrank as inverted_rank_range. Equal pairs are valid
• Defaults to quality_grade: ["research"] and captive: false, echoed back as applied_filters on every call
• per_page 1–25 (default 10); page walks the first 10,000 results under any ordering. Past that, order by id descending and pass each page's next_cursor as cursor — next_cursor is issued only on an id-descending page, since no other ordering can be continued by id. Passing page and cursor together fails, and a cursor forces the id ordering, which is echoed
• A page past the last one holding results says so and names that page, rather than suggesting wider filters
• include expands photos, annotations, sounds. identifications and comments are deliberately absent — one thread measures 28 KB, so the thread lives on inaturalist_get_observation

inaturalist_get_observation _tool

• 1–10 ids per call, resolved in a single upstream request
• include defaults to ["identifications"]; comments, photos, annotations, and sounds are also available
• Partial success: ids that resolve return in observations, the rest in unresolved; the call fails as not_found only when nothing resolved
• Adds community_taxon, identification_disagreements_count, the observer's description, and filled observation_fields on top of the projected search record
• Records come back in the requested order, unresolved ids left out in place
• identifications, comments, and the filled observation_fields share a 40-entry budget across the batch: each record keeps its first max(4, floor(40 / records returned)) entries per array in upstream order — 40 for one id, 4 for ten — and reports identifications_total/identifications_shown, comments_total/comments_shown, and observation_fields_total/observation_fields_shown. A cut is named in the notice; request one id alone for the 40-entry view, or open the record's url for the full record. description is never cut
• identifications_count is upstream's tally of identifications agreeing or disagreeing with the community taxon (agreements + disagreements), not the thread size — that is identifications_total

inaturalist_get_species_counts _tool

• Distinct species for an area and period, ranked by observation_count — the "what lives here" answer without paging through individual sightings
• Same area forms and filters as the observation search; taxon_id narrows to a clade, such as the birds of a park, and user_id/user_login or project_id to one observer's or one project's species list
• per_page 1–50 (default 25), page for offset — upstream would serve 500 in one page, and the cap is sized by response bytes instead
• Each row carries position, its absolute place in the ranking counted from page 1, and the rendered list is numbered from it — page 3 at 3 per page reads 7, 8, 9. rank stays the taxonomic rank
• truncationCeiling carries the last count shown; the ranking is descending, so nothing left off the page exceeds it

inaturalist_get_histogram _tool

• interval: month_of_year (default) and week_of_year fold every year into one seasonal curve; year, month, week, day, and hour bucket absolute dates, to which upstream applies its own default start date
• date_field: observed (default) or created
• taxon_id is optional — omit it to chart every taxon in the area
• term_id+term_value_id chart one life stage or reproductive state, such as monarch larvae (Life Stage 1 = Larva 6) or a plant in flower (Flowers and Fruits 12 = Flowers 13); iconic_taxa narrows to broad groups. term_value_id without term_id fails as unpaired_annotation_value, and an all-zero curve names the annotation or group filter when one was set
• Returns every bucket upstream produced in order, zeros included, plus their total — computed across every bucket upstream returned, even past the cap. day/hour over a wide date range can generate thousands of buckets, so the response is capped at 800, kept from the start of the range, with truncated/shown/cap disclosing the cut

inaturalist_get_leaderboard _tool

• kind: observers (ranked by observations recorded, carrying species_count) or identifiers (identifications made); count_metric names what count measures
• per_page 1–250 (default 25), page for offset. Both endpoints rank only the top 500, so page × per_page past 500 fails as leaderboard_window_exceeded rather than returning a false zero-hit
• Takes the same area forms, taxon_id, d1/d2, and quality_grade as the observation search

inaturalist_get_similar_species _tool

• The taxa a taxon_id is most often corrected from, ranked by misidentification_count — the field-identification check before committing to a look-alike
• taxon_id must be a genus or finer; upstream keeps no confusion set for a family, order, or anything coarser, and the call fails as taxon_rank_too_coarse
• An optional area, date range, quality_grade, and captive scope the confusion set to one region; omit them for the global set
• limit 1–50 (default 20), applied in-process — the endpoint publishes no page size and returns its whole set

inaturalist_get_taxon _tool

• One taxon_id. Returns kind: "full" with the projected profile, or kind: "outline" listing each section and its byte size when the projection still overflows the budget
• Sections are summary, taxonomy, children, conservation, photos, encyclopedia; name them in sections to fetch a slice, and an unknown name fails as unknown_section
• The upstream record is 95 KB for a common species — per-country checklist membership is dropped, listed_taxa_count kept as a scalar, and ancestors, children, and conservation entries trimmed to their identifying fields
• A named section comes back whole at whatever size, so sum the outline's byte sizes before asking for several

inaturalist://taxa/{taxon_id} _resource

• The projected taxon document as application/json, always whole — a resource read has no way to name sections, so use inaturalist_get_taxon when the outline path matters
• taxon_id comes from inaturalist_resolve_name; cached for six hours, matching the service's taxon TTL

inaturalist://observations/{observation_id} _resource

• One observation with its identification thread expanded, as application/json — the first 40 identifications and the first 40 filled observation fields in upstream order, each with its _total beside its _shown
• observation_id comes from inaturalist_search_observations; cached for fifteen minutes, since a thread accrues identifications

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

iNaturalist-specific:

• Keyless, read-only cover of the iNaturalist v1 API — observations, taxa, places, controlled terms, the similar-species graph, and the observer and identifier leaderboards
• Every response is projected in-process. Upstream accepts and ignores its own fields= parameter, so a two-record observation search arrives at 95 KB, a full upstream page of 200 at 4.3 MB, and a common taxon record at 95 KB before anything is trimmed
• Per-endpoint parameter allowlist — an unknown parameter name returns HTTP 200 and the entire global index, so nothing outside the allowlist is ever sent
• In-process rejection of every input upstream would silently widen, narrow to zero, or fail on: a lone lat, an unparseable or impossible d1 such as 2026-02-30, d1 after d2, a term_value_id without its term_id, user_id with user_login, a licence code outside the seven, a zero radius, a box with nelat south of swlat, a page past the result window
• Self-paced outbound traffic with a per-UTC-day request budget, since the API returns no rate-limit headers to react to

Agent-friendly output:

• Applied defaults echoed on every call — quality_grade, captive, and the ordering a cursor forced — so an agent can see the filters that shaped its answer
• Zero-hit notices name the filter most likely responsible and the tool that decodes it, instead of an empty list; a page past the end names the last page holding results instead
• Truncation disclosed unconditionally: truncated, shown, and cap on every path, plus a truncationCeiling where a descending ranking supports one
• Upstream free text — encyclopedia summaries, identification and comment bodies, place guesses, photo attributions — renders inside a markdown blockquote, marking it as third-party content rather than instruction

Licensing and attribution

The API is open; the records are not uniformly open.

• license_code is relayed verbatim and is nullable. A null means all rights reserved — it is never coerced to "", "unknown", or a default licence, and the rendered text spells the null case out in words.
• Photo attribution strings are relayed verbatim, never reformatted or shortened, and must be reproduced wherever the image is. A photo's own license_code is independent of its observation's.
• open is derived from the hosting domain: true for inaturalist-open-data.s3.amazonaws.com, false for anything else, because an unrecognised host is not evidence of an open licence. A licence change moves a photo between hosts, so the flag describes fetch time rather than a permanent property.
• Photos are linked, never proxied. No tool fetches image bytes or emits base64 image content — a URL with its attribution and licence is the whole contract.
• obscured: true marks a locality, not a sighting position. iNaturalist withholds true coordinates for threatened taxa, and the server never sends an Authorization header, so hidden coordinates stay hidden.
• Observer identity collapses to login. The upstream user object carries a real name, an ORCID, and counts; none of it is relayed.

Rate limits and response size

The published terms allow at most 100 requests per minute, ask clients to stay at or below 60, and ask for under 10,000 per day. No rate-limit headers come back, so pacing is entirely self-imposed: outbound requests start at least INATURALIST_MIN_REQUEST_INTERVAL_MS apart (1100 ms ≈ 54 per minute), at most INATURALIST_MAX_CONCURRENT_REQUESTS run in flight, and INATURALIST_DAILY_REQUEST_BUDGET bounds a UTC day. Exhausting the budget is a typed failure rather than a silent degradation.

Controlled terms (24 h), taxon profiles (6 h), places (6 h), the similar-species graph (6 h), and histograms (1 h) are cached in tenant-scoped storage. Observation search, species counts, leaderboards, and observation detail are never cached — freshness is what they are for.

Page-size maxima are sized by measured response bytes across structuredContent and the rendered text together, not by what upstream will serve:

Each default page fits the 24,000-byte budget a single document gets, and each full page fits 50,000. Nothing is unreachable at the lower caps — page walks the first 10,000 records under any ordering, and an id-descending walk continues past that by cursor — so the smaller page costs one more call rather than any data.

Known limitations

• Upstream ignores its own fields= partial-response parameter, so every byte is fetched before being projected away. Projection saves the agent's context, not the network.
• total_results is an estimate over a live index. It drifts between calls seconds apart.
• place_type and admin_level have no published code table. The raw integers are relayed and display_name carries the meaning.
• A place crossing the antimeridian has a degenerate bounding box upstream. It is relayed as computed, not repaired.
• Obscured coordinates cannot be resolved, by design. A threatened-taxon record reports a locality with an accuracy radius in the tens of kilometres.
• A section named in inaturalist_get_taxon comes back whole however large it is — truncating a section the caller asked for by name is the failure the outline exists to prevent.
• The daily request counter is per process. A restart resets it, and two processes behind one egress IP do not share it. Every caller of the public hosted instance draws on that one process's budget.
• inaturalist_get_leaderboard can address only the top 500 entries, against the 10,000-result window on observation search.

Getting started

Public Hosted Instance

A public instance is available at https://inaturalist.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "inaturalist-mcp-server": {
      "type": "streamable-http",
      "url": "https://inaturalist.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

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

Or with npx (no Bun required):

{
  "mcpServers": {
    "inaturalist-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/inaturalist-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "inaturalist-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/inaturalist-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.4.0 or higher (or Node.js ≥ 24.0.0).
• No API key required — the iNaturalist v1 API is keyless, and this server never authenticates.
• The published terms ask clients to identify themselves. A descriptive User-Agent with a contact URL is sent by default; keep one in any INATURALIST_USER_AGENT override.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/inaturalist-mcp-server.git

2. Navigate into the directory:

cd inaturalist-mcp-server

3. Install dependencies:

bun install

4. Configure environment (optional):

cp .env.example .env
# edit .env to override defaults — no required vars

Configuration

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run the production version:

  sh

  Copy

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http
  

• Run checks and tests:

  sh

  Copy

  bun run devcheck  # Lint, format, typecheck, security
  bun run test      # Vitest test suite
  bun run lint:mcp  # Validate MCP definitions against spec
  

Docker

docker build -t inaturalist-mcp-server .
docker run --rm -p 3010:3010 inaturalist-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/inaturalist-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for logging, ctx.state for storage
• Register new tools and resources in the createApp() arrays
• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.