Patent MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GCP_PROJECT_ID | No | GCP project ID with BigQuery enabled (required only for BigQuery search) | |
| GOOGLE_APPLICATION_CREDENTIALS | No | Path to GCP service account JSON key file (required only for BigQuery search) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_patentsA | Search global patents by keyword, country, CPC classification, or date range. At least one of country, cpc, or after must be provided to control query cost. Returns patent summaries with titles, abstracts, inventors, assignees, and CPC codes. CN patents include Chinese titles and abstracts. |
| get_patentA | Get full patent details by publication number (DOCDB format). Returns classifications, citations, family ID, dates, inventors, assignees. Citations include X/Y/A/D markers for prior art analysis. X=relevant if taken alone, Y=relevant if combined. |
| get_patent_claimsA | Get patent claims text by publication number. Claims define the legal scope of patent protection. Supports US, CN, and most other countries via Google Patents. |
| get_legal_statusA | Get legal status of a patent from Google Patents page. Extracts status (granted/application/utility_model), kind_code (A/B/U), filing_date, grant_date, priority_date, assignee, and legal events timeline. Works for CN, US, EP, and most other jurisdictions. |
| get_patent_familyA | Get patent family members for a patent. Finds family_id from BigQuery, then returns ALL patents sharing that family_id (same invention filed in different countries). Returns family_id, member_count, and members list with publication_number, country_code, kind_code, filing_date, grant_date, title for each. |
| batch_get_patentsA | Get full details for multiple patents in a single call. Much faster than calling get_patent N times separately. Returns list of PatentDetail objects. Max 20 patents per call. |
| batch_get_cited_byA | Get cited-by counts and lists for multiple patents in a single call. Returns list of {publication_number, cited_by_count, cited_by_patents, cited_by_url}. Max 10 patents per call. |
| get_cited_byB | Get backward citations (who cites this patent). Returns cited_by_count (int) and cited_by_patents (list of {publication_number, title, assignee}). Extracted from Google Patents HTML. |
| competitor_citation_matrixA | Check if a set of target patents are cited by competitors. Searches each patent's cited-by list and matches citing assignees against competitor keywords (case-insensitive substring). Returns matrix: {patent: [{citing_patent, title, assignee, matched_keyword}]} and summary counts. |
| bidirectional_citation_graphA | Build full bidirectional citation graph for a company's core patents. Searches for company's patents on Google Patents, then fetches forward and backward citations for each. If competitor_keywords provided, also runs competitor citation matrix. Returns: patents list, forward_graph, backward_graph, competitor_matrix. |
| company_summaryA | Get a quick patent portfolio summary for a company. Input a company name (Chinese or English), returns total patent count, top technology areas, jurisdiction coverage, activity level, and risk assessment. Zero BigQuery cost — scrapes Google Patents directly. Best for: initial company screening, competitor overview, due diligence triage. Typical latency: 5-10s. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Most tools target distinct resources/actions (claims, legal status, family, search, details). However get_cited_by, batch_get_cited_by, bidirectional_citation_graph, and competitor_citation_matrix all center on citation data, which could cause some misselection, though descriptions clarify single vs batch vs graph vs competitor scope.
A dominant verb_noun pattern (get_patent, search_patents, get_patent_claims, get_legal_status, get_patent_family, get_cited_by) with a consistent batch_ prefix is clear. A few noun-phrase outliers (bidirectional_citation_graph, competitor_citation_matrix, company_summary) lack verbs but remain readable.
11 tools is well-scoped for a patent analysis server, with each tool earning its place across details, claims, legal status, family, citations, search, batch variants, and company screening.
Strong coverage of the patent lifecycle: details, claims, legal status, family, citations, search, and portfolio summary. Minor gaps exist (e.g. no direct assignee/inventor patent listing or full description/figures retrieval), but core workflows are covered.