Atlas / MCP servers / deeparchi-ai / patent-mcp-server

patent-mcp-serverCAUTION

mcp/deeparchi-ai/patent-mcp-server

MCP Server for global patent data retrieval and analysis, powered by Google Patents Public Datasets on BigQuery. MIT.

Verdict
CAUTION
Grade
B
Trust score
89 /100
Exposed tools
—
Transport
stdio
License
MIT
Stars
2
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

🚀 中国专利最准确的开源 MCP。 Give your AI agent the ability to read CN patents with real accuracy — plus global coverage.

[](https://github.com/deeparchi-ai/patent-mcp-server/actions) [](https://www.python.org/) [](LICENSE) [](https://modelcontextprotocol.io/) [](https://pypi.org/project/deeparchi-patent-mcp/)

An MCP (Model Context Protocol) server that gives AI agents access to patent data — CN patents with CPC-aware correction, plus US/WO global coverage. Runs locally on your machine. No external API, no subscription. Always MIT.

Why Self-Deployed

  • It's just Python. Install it, your agent uses it. No server to maintain, no credential to share.
  • No API key for 80% of use cases. Patent details and claims come straight from Google Patents public pages.
  • Your data stays local. Nothing leaves your machine except the same HTTP requests a browser would make.
  • BigQuery search is optional. Only turn it on if you need full-text search across 1.4B records.

30-Second Install

pip install deeparchi-patent-mcp

Or from source:

git clone https://github.com/deeparchi-ai/patent-mcp-server.git
cd patent-mcp-server
pip install -e .

Quick Start

After pip install, the deeparchi-patent-mcp console script is on your PATH. Add this to your agent platform's MCP config:

Claude Desktop

{
"mcpServers": {
"patent-mcp": {
"command": "deeparchi-patent-mcp",
"args": []
}
}
}

Cursor / Windsurf / Cline

Same config as Claude Desktop above.

Hermes Agent

mcp_servers:
patent-mcp:
command: "
Read from source at commit 8b8e4201e8f1OBSERVED · 2026-10-11
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (pypi)
claude mcp add deeparchi-patent-mcp -- None deeparchi-patent-mcp==1.9.2
03

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (8 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (6)

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
run.sh:5
export HTTPS_PROXY="http://127.0.0.1:7897"
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
run.sh:6
export HTTP_PROXY="http://127.0.0.1:7897"
MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319
src/web/google_patents.py:31
SEARXNG_URL = os.environ.get("SEARXNG_URL", "http://127.0.0.1:8888")
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
docs/立项书-patent-mcp-cloud.md:103
1. `src/web/google_patents.py:42` — `PROXIES` 字典通过 `if os.environ.get("HTTPS_PROXY") or True` 强制启用,即使未设环境变量也会 fallback 到 `http://127.0.0.1:7897`(Clash Verge)
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:19
- **It's just Python.** Install it, your agent uses it. No server to maintain, no credential to share.
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
LOWInventory / provenance · mcp.no_tools_extracted · CWE-1104
server.json
Why it matters. the tool list is enumerated at runtime by tools/list, not declared in source
Fix. the page says so rather than showing an empty table

Gates applied: no_behavioural_pass.

Audited 2026-10-11 · audit v0.4.1 · source sha 8b8e4201e8f1full audit observations/trust-audit/mcp-server/deeparchi-ai__patent-mcp-server.json · Report an issue / request a re-scan
04

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-118b8e4201e8f1CAUTIONB89first audit
05

Questions

What is the patent-mcp-server MCP server?

MCP Server for global patent data retrieval and analysis, powered by Google Patents Public Datasets on BigQuery. MIT.

Is patent-mcp-server safe to connect to an agent?

With care. The audit graded it B (89/100) and found 6 things worth knowing before you trust this server, listed below with the exact line each was found on.

What credentials does patent-mcp-server need?

It reads FIRECRAWL_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does patent-mcp-server run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as deeparchi-patent-mcp.

How current is this page?

The grade is for one exact copy of the source (8b8e4201e8f1), read on 2026-10-11. The repository is watched and re-audited when it changes.

Advertisement