Inaturalist

Search Observations

search_observations

Read-onlyIdempotent

Search citizen-science wildlife observations on iNaturalist — ANY organism: plants, fungi, insects, birds, mammals, reptiles, amphibians. This is the tool for "sightings/observations of in in ". Filter by taxon name (scientific or common, e.g. "Leucanthemum vulgare"/"oxeye daisy", "Pandion haliaetus"/"osprey"), place name ("Yukon", "California"), year, threatened status, or quality grade. Returns photographed sightings with coordinates, dates, and observer info. Pairs well with GBIF for cross-validation.

Input Schema

TableJSON Schema

Name	Required	Description
`year`	No	Filter to a specific year
`place`	No	Place name (country, state, park). Auto-resolved to place_id.
`per_page`	No	Results per page (1-200, default 20)
`taxon_name`	No	Scientific or common species/taxon name
`threatened`	No	Restrict to IUCN-threatened taxa
`quality_grade`	No	casual \| needs_id \| research (default: research)

Output Schema

TableJSON Schema

Name	Required	Description
`resolved`	Yes	Resolved taxon and place IDs from input names
`observations`	Yes	Array of observation records
`total_results`	Yes	Total observation count matching filters

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 27, 2026

addedOutput schema / properties / resolved / properties / taxon / properties / rank

Added value: +{
+  "description": "Taxonomic rank of the resolved taxon (species, genus, family, ...)",
+  "type": [
+    "string",
+    "null"
+  ]
+}

Changed2 schema fields changedMay 22, 2026

addedInput schema / examples

Added value: +[
+  {
+    "place": "California",
+    "quality_grade": "research",
+    "taxon_name": "Pandion haliaetus"
+  },
+  {
+    "per_page": 50,
+    "taxon_name": "osprey",
+    "threatened": true,
+    "year": 2023
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "observations": {
+      "description": "Array of observation records",
+      "items": {
+        "properties": {
+          "id": {
+            "description": "Observation ID",
+            "type": "number"
+          },
+          "latitude": {
+            "description": "Latitude coordinate",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "longitude": {
+            "description": "Longitude coordinate",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "observed_on": {
+            "description": "ISO date observed",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "observer": {
+            "description": "Observer login name",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "photo": {
+            "description": "Photo URL",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "place": {
+            "description": "Place guess from observation",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "quality_grade": {
+            "description": "Quality grade (casual, needs_id, research)",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "taxon": {
+            "properties": {
+              "common_name": {
+                "description": "Common name",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "id": {
+                "description": "Taxon ID",
+                "type": "number"
+              },
+              "rank": {
+                "description": "Taxonomic rank",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "scientific_name": {
+                "description": "Scientific name",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "type": [
+              "object",
+              "null"
+            ]
+          },
+          "url": {
+            "description": "iNaturalist observation URL",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "resolved": {
+      "description": "Resolved taxon and place IDs from input names",
+      "properties": {
+        "place": {
+          "properties": {
+            "id": {
+              "description": "iNaturalist place ID",
+              "type": "number"
+            },
+            "name": {
+              "description": "Place name",
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "taxon": {
+          "properties": {
+            "id": {
+              "description": "iNaturalist taxon ID",
+              "type": "number"
+            },
+            "name": {
+              "description": "Taxon name",
+              "type": "string"
+            }
+          },
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    "total_results": {
+      "description": "Total observation count matching filters",
+      "type": "number"
+    }
+  },
+  "required": [
+    "resolved",
+    "total_results",
+    "observations"
+  ],
+  "type": "object"
+}

First observedMay 11, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, etc. Description adds that results are 'photographed sightings with coordinates, dates, and observer info' and that place auto-resolves to place_id. No harmful behavior, but adds useful context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single paragraph front-loads purpose and then details filters and return fields. While slightly dense, every sentence adds value and the description is efficient for the information conveyed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With output schema present and annotations covering safety, the description provides all essential usage details: filters, return fields, and cross-validation hint. No gaps remain for an agent to use this tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3). Description adds examples of taxon names (common and scientific), clarifies that place auto-resolves, and lists filterable criteria in a narrative form, providing extra value over the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description explicitly states verb ('Search'), resource ('citizen-science wildlife observations on iNaturalist'), and scope ('ANY organism'). Provides examples of filterable criteria and contrasts with sibling tool GBIF, making purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear usage pattern ('sightings/observations of <species> in <place> in <year>') and suggests pairing with GBIF. However, does not explicitly state when not to use or compare with sibling tool 'search_taxa'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Inaturalist tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.