Epo Ops

Get Claims

get_claims

Read-onlyIdempotent

Fetch the full claims text of a published patent from EPO OPS. EPO's full-text collection is narrower than its bibliographic one — European (EP) and PCT (WO) publications have the broadest claims coverage, and a publication outside that collection comes back as found:false naming get_biblio as the route to its title, applicants and abstract. Give the publication number as printed on the document; a trailing kind code is handled for you. Requires _apiKey=consumer_key:consumer_secret.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`number`	Yes	Publication number as printed on the document, e.g. "EP1234567", "CN117928705A", "US10000000", or a PCT international publication like "WO2025028566" / "WO 2025/028566" / "WO2025028566A1". Spaces, commas and slashes are ignored, and a trailing kind code (the "A" / "A1" / "B1" suffix) is retried without it if the exact form is not indexed.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`claims`	No	Claims data

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 20, 2026

changedInput schema / properties / number / description

Previous value: -"Publication number as printed on the document, e.g. \"EP1234567\", \"CN117928705A\", \"US10000000\". Spaces, commas and slashes are ignored, and a trailing kind code (the \"A\" / \"A1\" / \"B1\" suffix) is retried without it if the exact form is not indexed."New value: +"Publication number as printed on the document, e.g. \"EP1234567\", \"CN117928705A\", \"US10000000\", or a PCT international publication like \"WO2025028566\" / \"WO 2025/028566\" / \"WO2025028566A1\". Spaces, commas and slashes are ignored, and a trailing kind code (the \"A\" / \"A1\" / \"B1\" suffix) is retried without it if the exact form is not indexed."

Changed2 schema fields changedAug 6, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "number": "EP1234567"
-  }
-]New value: +[
+  {
+    "number": "EP1000000"
+  }
+]

changedInput schema / properties / number / description

Previous value: -"Patent number, epodoc format"New value: +"Publication number as printed on the document, e.g. \"EP1234567\", \"CN117928705A\", \"US10000000\". Spaces, commas and slashes are ignored, and a trailing kind code (the \"A\" / \"A1\" / \"B1\" suffix) is retried without it if the exact form is not indexed."

Changed2 schema fields changedMay 22, 2026

addedInput schema / examples

Added value: +[
+  {
+    "number": "EP1234567"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Claims text and structure for a patent",
+  "properties": {
+    "claims": {
+      "description": "Claims data",
+      "properties": {
+        "claim": {
+          "oneOf": [
+            {
+              "type": "object"
+            },
+            {
+              "description": "Individual claims with claim numbers and text",
+              "items": {
+                "type": "object"
+              },
+              "type": "array"
+            }
+          ]
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

First observedMay 13, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnly/openWorld/idempotent/non-destructive) by disclosing coverage narrowness, the found:false failure shape, automatic kind-code retry, and the _apiKey=consumer_key:consumer_secret auth requirement. These are exactly the operational facts an agent needs before calling.

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?

Front-loaded with the action, then coverage caveat, parameter handling, and auth in descending priority. Dense but every clause carries information; the em-dash aside about EP/WO is the only slightly verbose element.

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?

An output schema exists, so return values need not be described, yet the description still covers the one surprising return case (found:false) and the auth prerequisite. Nothing needed to call this 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% and the 'number' property is already documented in detail (formats, space/comma/slash handling, kind-code retry). The description only restates 'as printed on the document' and 'a trailing kind code is handled for you', adding little beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource ('Fetch the full claims text of a published patent') plus the source system (EPO OPS). It implicitly but clearly distinguishes itself from sibling metadata tools by naming the claims text as its output and routing metadata needs to get_biblio.

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?

Explains the coverage constraint (EP/PCT broadest) and tells the agent exactly what to do when a publication falls outside the collection: it returns found:false and points at get_biblio for title/applicants/abstract. That is a concrete alternative with a triggering condition, though it never states an explicit 'prefer this over X' rule.

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

All Epo Ops 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.