Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Patent MCP Server

PYPI · DEEPARCHI-PATENT-MCP

Patent search over 1.4B global records via Google Patents on BigQuery, with CN coverage.

+10 this week 81 Trust /100

Last scanned (21 hours ago)

Scores higher than 82% of PyPI servers

Category Education and Research

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 0 of 52 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability82
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1189 tokens (~108/item across 11 items; 11 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
  • Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Nov 26 +10
    • Malware scan: unverified → pass ▲ security
    • Stability: pass → 0.63 functional
  • 2 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 1 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 31 Oct 26 −15
    • Malware scan: pass → unverified ▼ security
  • 29 Oct 26 +15
    • Malware scan: unverified → pass ▲ security
  • 28 Oct 26 +1
    • Stability: 0.97 → pass security
  • 26 Oct 26 −14
    • Malware scan: pass → unverified ▼ security
  • 24 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Analysed pypi/deeparchi-patent-mcp@1.9.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 52 packages
Packages resolved 52
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~1,189 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
batch_get_cited_by ~72

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.

NameTypeReqDescription
publication_numbersarrayyesPatent publication numbers (e.g. CN110286864A)

No output schema declared.

No examples provided.

batch_get_patents ~66

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.

NameTypeReqDescription
publication_numbersarrayyesPatent publication numbers (e.g. CN110286864A)

No output schema declared.

No examples provided.

bidirectional_citation_graph ~125

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.

NameTypeReqDescription
assignee_namestringyesCompany name for patent search, e.g. 'Wuhan Carbit'
competitor_keywordsarray–Optional competitor substrings, e.g. 百度, 华为
limitinteger–Max patents to analyze (default 10)

No output schema declared.

No examples provided.

company_summary ~113

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.

NameTypeReqDescription
company_namestringyesCompany name in Chinese or English. e.g. '正浩创新', 'Anker Innovations', 'DJI'

No output schema declared.

No examples provided.

competitor_citation_matrix ~116

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.

NameTypeReqDescription
competitor_keywordsarrayyesCompetitor assignee substrings, e.g. 百度, Baidu, 华为
publication_numbersarrayyesPatent numbers to check (e.g. CN110286864A)

No output schema declared.

No examples provided.

get_cited_by ~82

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.

NameTypeReqDescription
publication_numberstringyesPatent publication number, e.g. 'US-7650331-B1', 'CN-110286864-A'

No output schema declared.

No examples provided.

get_legal_status ~101

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.

NameTypeReqDescription
publication_numberstringyesPatent publication number, e.g. 'US-7650331-B1', 'CN-110286864-A'

No output schema declared.

No examples provided.

get_patent ~95

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.

NameTypeReqDescription
publication_numberstringyesPatent publication number, e.g. 'US-7650331-B1', 'CN-103257828-A'

No output schema declared.

No examples provided.

get_patent_claims ~73

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.

NameTypeReqDescription
publication_numberstringyesPatent publication number, e.g. 'US-7650331-B1', 'CN-103257828-A'

No output schema declared.

No examples provided.

get_patent_family ~102

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.

NameTypeReqDescription
publication_numberstringyesPatent publication number, e.g. 'US-7650331-B1', 'CN-110286864-A'

No output schema declared.

No examples provided.

search_patents ~244

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.

NameTypeReqDescription
afterstring–Earliest filing date, format YYYY-MM-DD
assigneestring–Optional assignee/organization name filter (fuzzy match on harmonized names). Use for company-level or city-level analysis, e.g. 'HEFEI', 'BOE', 'HUAWEI'.
beforestring–Latest filing date, format YYYY-MM-DD
countrystring–Country code filter, e.g. 'CN', 'US', 'EP'
cpcstring–CPC classification code prefix, e.g. 'G06F40', 'H01L'
limitinteger–Maximum results (default 10, max 50)
querystring–Optional keyword/technology area/inventor name to search
statusstring–Patent status filter

No output schema declared.

No examples provided.

Install

How do I install the Patent MCP Server server?

Patent MCP Server runs locally as a PyPI package, launched with uvx deeparchi-patent-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · deeparchi-patent-mcp

# add to Claude Code
claude mcp add deeparchi-ai-patent-mcp-server -- uvx deeparchi-patent-mcp
Common questions

What is the Patent MCP Server server?

Patent MCP Server is listed in the public MCP registry as io.github.deeparchi-ai/patent-mcp-server. Patent search over 1.4B global records via Google Patents on BigQuery, with CN coverage. This page covers its PyPI package (deeparchi-patent-mcp).

Is the Patent MCP Server server safe to use?

Patent MCP Server scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Patent MCP Server server expose?

Patent MCP Server exposes 11 tools: search_patents, get_patent, get_patent_claims, get_legal_status, get_patent_family, and 6 more. Their descriptions and schemas cost roughly 1,189 tokens of context every time the server is loaded.

Is the Patent MCP Server server still maintained?

Patent MCP Server is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Patent MCP Server server under?

Patent MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.