io.github.cyanheads/inaturalist-mcp-server
io.github.cyanheads/inaturalist-mcp-server
Search iNaturalist sightings, identification threads, phenology, and look-alike species.
Connect this server
Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.
{
"mcpServers": {
"inaturalist-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/inaturalist-mcp-server@0.3.2"
],
"env": {
"MCP_LOG_LEVEL": "info",
"INATURALIST_CLAMP_LIMITS": "true",
"INATURALIST_MIN_REQUEST_INTERVAL_MS": "1100",
"INATURALIST_MAX_CONCURRENT_REQUESTS": "4",
"INATURALIST_DAILY_REQUEST_BUDGET": "9000"
}
}
}
}- MCP_LOG_LEVELSets the minimum log level for output (e.g., 'debug', 'info', 'warn').
- INATURALIST_CLAMP_LIMITSClamp oversized read limits and radius (20,040 km), and defer oversized by-id batches. Set false to restore strict rejection, including radius above 500 km.
- INATURALIST_MIN_REQUEST_INTERVAL_MSMinimum spacing between outbound request starts, in milliseconds. The default holds the sustained rate near 54 requests per minute, under the 60 the upstream asks for and well under its 100 ceiling.
- INATURALIST_MAX_CONCURRENT_REQUESTSMaximum outbound requests in flight. Separate from the start interval: spacing bounds the sustained rate, this bounds the burst so one slow call does not stall the lane.
- INATURALIST_DAILY_REQUEST_BUDGETOutbound requests allowed per UTC day, counted in-process. The default sits under the 10,000 per day the upstream asks for, and exhaustion fails loudly rather than degrading silently. The counter is per process and resets on restart.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Developer Tools
- Version
- 0.3.2
- Registry
- active
- Published
- 11/1/2026
Remotes
- streamable-http
https://inaturalist.caseyjhand.com/mcp
More Developer Tools servers
Browse all Developer Tools →io.github.cyanheads/internet-archive-mcp-server
cyanheads
Search the Wayback Machine and IA library (40M+ items), fetch snapshots, item metadata, and text.
io.github.cyanheads/interpro-mcp-server
cyanheads
Search InterPro entries, map domains onto proteins and PDB structures, and scan raw sequences.
io.github.cyanheads/ioda-outages-mcp-server
cyanheads
Investigate Internet outages with IODA events, alerts, and connectivity signals via MCP.
io.github.cyanheads/libofcongress-mcp-server
cyanheads
Search LOC digital collections, Chronicling America newspapers (full OCR), and LC Subject Headings.
io.github.cyanheads/macos-mcp-server
cyanheads
Control macOS settings, apps, windows, audio, Music, displays, screenshots, and Focus mode via MCP.
io.github.cyanheads/mailchimp-mcp-server
cyanheads
Mailchimp via MCP: draft, test, and send campaigns; manage audiences and subscribers; pull reports.
Add the badge to your site
Show visitors that io.github.cyanheads/inaturalist-mcp-server is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-cyanheads-inaturalist-mcp-server?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="io.github.cyanheads/inaturalist-mcp-server — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-cyanheads-inaturalist-mcp-server?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.