mcpField
P
Pondlog iNaturalist

Pondlog iNaturalist

Local
github.com/andrewschristisonScience & Education0Updated 3w ago

About Pondlog iNaturalist

Pondlog iNaturalist is an MCP server for developers working with nature data, providing access to wildlife observations, species counts, taxa, and places worldwide. It wraps iNaturalist data as tools for AI agents and runs without an API key.

Key features

  1. 01Search nearby iNaturalist observations
  2. 02Retrieve species counts and taxonomy
  3. 03Explore wildlife data by place
  4. 04Run without an API key

Use cases

  1. 01Find recent animal observations near coordinates
  2. 02Review species records and taxonomy by place
  3. 03Let an AI agent query iNaturalist data

MCP support

The MCP server exposes iNaturalist data-query tools to MCP clients. It can be launched with npx and does not require an API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"andrewschristison-pondlog-inaturalist": {
"command": "npx",
"args": [
"-y",
"@pondlog/mcp-inaturalist"
]
}
}
}
Run commandnpx -y @pondlog/mcp-inaturalist

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@pondlog/mcp-inaturalist0.1.3

Tools

9

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
d1stringNoStart date (inclusive), ISO YYYY-MM-DD. Example: 2025-04-01.
d2stringNoEnd date (inclusive), ISO YYYY-MM-DD. Example: 2025-04-30.
latnumberNoWGS84 latitude in decimal degrees, between -90 and 90. Example: 48.118 for Port Angeles, WA.
lngnumberNoWGS84 longitude in decimal degrees, between -180 and 180. Example: -123.4307 for Port Angeles, WA.
pageintegerNoPage number, 1-indexed. iNaturalist caps page * per_page at 10,000.
order_byenumNoSort order. 'observed_on' for chronological by sighting date (most useful); 'created_at' for upload order; 'votes' for community-favorited.created_at | observed_on | species_guess | votes | id
per_pageintegerNoResults per page. Default 30, maximum 200.
place_idintegerNoiNaturalist place ID. Use `search_places` first to look one up. Filters to a named region rather than lat/lng radius.
radius_kmnumberNoGeographic search radius in km. Required if `lat`/`lng` are provided. Default 25 when geo-searching. Maximum 500.
taxon_namestringNoTaxon name to filter by. Accepts common name (e.g. 'frog', 'bald eagle') or scientific name (e.g. 'Pseudacris regilla'). Partial matches work.
iconic_taxaarrayNoFilter to one or more iNaturalist iconic-taxa groups. Aves = birds; Amphibia = frogs, salamanders, newts; Mammalia = mammals; Reptilia = reptiles; Insecta = insects; Arachnida = spiders, scorpions, mites; Mollusca = snails, slugs, clams, octopuses; Plantae = plants; Fungi = fungi, lichens; Actinopterygii = ray-finned fish; Animalia = catch-all animal kingdom (use only when others don't fit); Protozoa, Chromista = microscopic eukaryotes.
quality_gradeenumNoiNaturalist quality grade. 'research' = community-verified IDs (most reliable); 'needs_id' = uploaded but not yet verified; 'casual' = excluded from research-grade pool. Default: no filter (all grades).research | needs_id | casual

Details

From the project README

pondlog

Place-aware nature data for developers. What's happening in nature at these coordinates right now?

Pondlog stitches together free public APIs (iNaturalist, eBird, USA-NPN, USGS, Mushroom Observer) plus local astronomy computation (astronomy-engine) and NOAA tides/cloud cover into one data layer with two interfaces:

  • A CLI for humans (pondlog inat nearby --lat 48.118 --lng -123.43)
  • An MCP server per source for AI agents (Claude Desktop, Cursor)

By Andrew Christison.

What's in the box

8 data sources. 7 MCP servers. 1 unified CLI. A ~1000-crop garden planner with USDA hardiness zones and companion-planting graph.

PackagenpmWhat it does
pondlognpmUnified CLI
@pondlog/corenpmShared types, Result<T>, rate limiter, USDA zones, crop calendar, companions
@pondlog/source-inaturalistnpmiNaturalist API client
@pondlog/source-ebirdnpmeBird API client (21 endpoints)
@pondlog/source-npnnpmUSA-NPN phenology client
@pondlog/source-usgsnpmUSGS Water Services client
@pondlog/source-nightskynpmLocal night-sky briefing (astronomy-engine)
@pondlog/source-mushroomobservernpmMushroom Observer (mycology) client
@pondlog/source-treflenpmTrefle.io plant taxonomy client
@pondlog/mcp-inaturalistnpmiNaturalist MCP server (9 tools)
@pondlog/mcp-ebirdnpmeBird MCP server (21 tools)
@pondlog/mcp-npnnpmNPN MCP server (8 tools)
@pondlog/mcp-usgsnpmUSGS MCP server (4 tools)
@pondlog/mcp-mushroomobservernpmMushroom Observer MCP server (5 tools, mycology-first)
@pondlog/mcp-gardennpmGarden-planning MCP server (8 tools, calendar + zones + companions + Trefle)
@pondlog/mcp-pondlognpmAggregate MCP server (5 tools, all eight sources)

Status

SourceLibraryCLIMCP
iNaturalist✅✅✅
eBird✅✅✅
NPN (phenology)✅✅✅
USGS (water)✅✅✅
Mushroom Observer (mycology)✅✅✅
Garden (USDA zones + ~5,000-crop calendar + companions + Trefle)✅✅✅
Night sky (astronomy-engine)✅✅✅ (via mcp-pondlog)
Aggregate (pondlog today / mcp-pondlog)n/a✅✅

Quick start

As an AI agent (MCP)

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

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

Then ask Claude:

What amphibians have been seen near Port Angeles, WA in the last week?

The same JSON works in ~/.cursor/mcp.json for Cursor. Run any MCP server in one command:

npx -y @pondlog/mcp-inaturalist          # no key
npx -y @pondlog/mcp-garden               # offline garden tools
EBIRD_API_KEY=... npx -y @pondlog/mcp-ebird
npx -y @pondlog/mcp-pondlog              # aggregate of all eight sources
As a human (CLI)
npm install -g pondlog
pondlog config set-location --lat 48.118 --lng -123.4307 --name "Port Angeles"
pondlog today                          # unified briefing
pondlog inat nearby
pondlog ebird notable
pondlog npn active
pondlog usgs flow --site 12045500
pondlog nightsky                       # tonight's curated briefing
pondlog garden now                     # what to plant this week

--json works on every command for machine output.

Architecture

                          ┌─────────────────────────┐
                          │      @pondlog/core      │
                          │  types, Result<T>,      │
                          │  RateLimiter, withRetry,│
                          │  USDA zones, crops,     │
                          │  companion graph        │
                          └────────────┬────────────┘
                                       │
        ┌──────────┬──────────┬────────┼─────────┬──────────┬──────────┐
        ▼          ▼          ▼        ▼         ▼          ▼          ▼
 source-inat  source-ebird  source-npn  source-usgs  source-mo  source-trefle  source-nightsky
        │          │          │        │         │          │          │
        └──────────┴──────────┴────────┼─────────┴──────────┴──────────┘
                                       │
                  ┌────────────────────┴────────────────────┐
                  ▼                                         ▼
            pondlog (CLI)                       7 × @pondlog/mcp-* servers
            ├─ pondlog today (aggregate)         ├─ mcp-inaturalist
            ├─ pondlog inat/ebird/...             ├─ mcp-ebird
            └─ pondlog garden/nightsky            ├─ mcp-npn / mcp-usgs
                                                  ├─ mcp-mushroomobserver
                                                  ├─ mcp-garden
                                                  └─ mcp-pondlog  ◀── aggregate

Source clients do all the work (Zod validation, rate limiting, retry, normalization). The CLI and MCP servers are thin wrappers around them.

Design principles

  • One data layer, two interfaces. Each source is a typed library (Zod-validated, rate-limited, returns Result<T>). The CLI and MCP servers are thin wrappers. No business logic in them.
  • Degrade gracefully. When a source is down, the aggregate still returns whatever else worked, with errors reported in-band.
  • Rate limits respected. Each client throttles itself. Never trust the caller.
  • No keys for what doesn't need them. iNaturalist, NPN, USGS, Mushroom Observer, and the night-sky source all run keyless. Only eBird and Trefle require free keys.
  • Local computation when the data isn't external. Astronomy is pure math; @pondlog/source-nightsky ships zero network calls, zero rate limits, zero failure modes. The garden calendar, zones, and companion graph are bundled JSON, all offline.

Related: CropGraph

CropGraph is a sibling HTTP API exposing the same ~1000-crop planting calendar, USDA hardiness zones, and companion-planting graph used by @pondlog/core and @pondlog/mcp-garden. Use CropGraph when you want the data over HTTP from any language. The schemas are kept in lockstep with this repo.

Contributing

PRs welcome. The build is pnpm-based:

git clone https://github.com/andrewschristison/pondlog.git
cd pondlog
pnpm install
pnpm typecheck
pnpm build
pnpm test
pnpm smoke   # live tests against iNaturalist
Crop calendar / companion-planting data

The crop calendar (packages/core/src/data/crop-calendar.json) and companion graph (packages/core/src/data/companions.json) accept community PRs. Both have JSON Schemas alongside the data:

  • packages/core/src/data/crop-calendar.schema.json
  • packages/core/src/data/companions.schema.json

When adding a crop entry, include a per-entry source citing a real extension service (USDA, Cornell, WSU, Oregon State, UMass, UF/IFAS, etc.). When adding a companion edge, include evidence (strong or moderate) and a citation URL. Zod validation runs at module load, so a malformed PR breaks import "@pondlog/core" immediately.

Code

Each package follows a strict pattern documented in docs/METHODOLOGY.md. Source clients always ship before the CLI commands or MCP tools that consume them.

License

MIT. See LICENSE.

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.