Patents

Search Inventors

search_inventors

Read-onlyIdempotent

Search USPTO patent applications by inventor last name. Returns matching applications with title, inventor list, and filing date — sorted newest-filed-first, so this is the APPLICATION corpus (same as search_patents with no granted_after), and the newest rows will be unexamined filings with no grant date by construction (USPTO publishes ~18 months after filing). That is expected, not stale data. For a specific inventor's ISSUED patents, use search_patents with inventor + granted_after instead.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "Smith"
    },
    "name": "search_inventors"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Number of results to return (default 10). USPTO caps every search at 25 records, so values above 25 have no effect — use the filters to narrow instead.
`query`	Yes	Inventor last name to search for (case-insensitive). Examples: "Hinton", "Bengio".
`_apiKey`	No	USPTO ODP API key. Get free at https://data.uspto.gov/myodp.

Output Schema

Name	Required	Description
`query`	Yes	The search query used
`returned`	Yes	Number of inventors in this response
`inventors`	Yes	List of inventor details
`total_results`	Yes	Total number of matching inventors

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 1, 2026

changedInput schema / properties / limit / description

Previous value: -"Number of results (1–100, default 10)."New value: +"Number of results to return (default 10). USPTO caps every search at 25 records, so values above 25 have no effect — use the filters to narrow instead."

Changed1 schema field changedJul 29, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "query": "Smith"
-  },
-  {
-    "per_page": 15,
-    "query": "Johnson"
-  }
-]New value: +[
+  {
+    "query": "Smith"
+  },
+  {
+    "query": "Johnson"
+  }
+]

Changed4 schema fields changedMay 12, 2026

addedInput schema / properties / _apiKey

Added value: +{
+  "description": "USPTO ODP API key. Get free at https://data.uspto.gov/myodp.",
+  "type": "string"
+}

addedInput schema / properties / limit

Added value: +{
+  "description": "Number of results (1–100, default 10).",
+  "type": "number"
+}

removedInput schema / properties / per_page

Removed value: -{
-  "description": "Number of results to return (default 10, max 25)",
-  "type": "number"
-}

changedInput schema / properties / query / description

Previous value: -"Inventor last name to search for"New value: +"Inventor last name to search for (case-insensitive). Examples: \"Hinton\", \"Bengio\"."

Changed1 schema field changedMay 8, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "inventors": {
+      "description": "List of inventor details",
+      "items": {
+        "properties": {
+          "city": {
+            "description": "Inventor city or null",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "first_name": {
+            "description": "Inventor first name or null",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "last_name": {
+            "description": "Inventor last name or null",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "patent_numbers": {
+            "description": "Patent numbers associated with inventor",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "state": {
+            "description": "Inventor state or null",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "query": {
+      "description": "The search query used",
+      "type": "string"
+    },
+    "returned": {
+      "description": "Number of inventors in this response",
+      "type": "number"
+    },
+    "total_results": {
+      "description": "Total number of matching inventors",
+      "type": "number"
+    }
+  },
+  "required": [
+    "query",
+    "total_results",
+    "returned",
+    "inventors"
+  ],
+  "type": "object"
+}

Changed1 schema field changedMay 6, 2026

addedInput schema / examples

Added value: +[
+  {
+    "query": "Smith"
+  },
+  {
+    "per_page": 15,
+    "query": "Johnson"
+  }
+]

First observedApr 14, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the ~18-month publication lag, that unexamined filings lacking grant dates are expected rather than stale, and the corpus-level difference from search_patents. This preempts a realistic false conclusion about data quality.

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?

Well organized: the core purpose and return fields are front-loaded, followed by the corpus explanation and the alternative routing. Every sentence earns its place, though the passage is dense enough that the key facts are spread across several clauses that a fast reader could skim past.

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?

Covers return shape (title, inventor list, filing date), sort order (newest-first), the corpus semantics, the freshness expectation, and the alternative tool. An output schema exists and the limit cap lives in the parameter schema. Nothing an agent needs to invoke it correctly is missing.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all three parameters (query, limit, _apiKey). The description adds minimal parameter-level detail beyond the schema -- it reinforces that `query` is the inventor last name and echoes the 25-record cap already present in the schema's `limit` description. Baseline 3 is appropriate.

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?

Opens with a specific verb+resource+filter: 'Search USPTO patent applications by inventor last name.' It explicitly disambiguates against the sibling search_patents by stating this is the APPLICATION corpus (same as search_patents with no `granted_after`), so an agent can tell them apart without inspecting schemas.

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

Usage Guidelines5/5

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

Gives explicit routing: 'For a specific inventor's ISSUED patents, use search_patents with `inventor` + `granted_after` instead.' It also tells the agent what this tool is for (applications) versus what it is not (issued patents), and cautions that newest rows will be unexamined filings -- preventing a wrong inference.

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

All Patents 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.