Claude-Patent-Creator

An AI-assisted patent drafting and analysis system for Claude Code that combines (1) an MCP server exposing tools for MPEP/USC/CFR regulation search via hybrid RAG, (2) large-scale patent search via Google BigQuery (public patent datasets) plus optional USPTO API checks, (3) automated 35 USC 112(a)/(b) and formalities-style reviews, and (4) diagram generation using Graphviz.

Evaluated Mar 30, 2026 (21d ago)
Homepage ↗ Repo ↗ Ai Ml ai-ml patent rag bigquery mcp-server claude-code graphviz compliance-check
⚙ Agent Friendliness
52
/ 100
Can an agent use this?
🔒 Security
48
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
70
Error Messages
0
Auth Simplicity
55
Rate Limits
20

🔒 Security

TLS Enforcement
60
Auth Strength
45
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
60

Uses environment variables for API keys and suggests Google Cloud ADC for BigQuery. No explicit guidance is provided about MCP server auth, least-privilege scopes, or how secrets are redacted in logs. TLS expectations are not specified for MCP/any endpoints (likely local), and dependency hygiene/CVE status cannot be determined from provided content.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
40
Error Recovery
30
AF Security Reliability

Best When

You want an agent/tooling workflow inside Claude Code that can search regulations and patents, perform heuristic compliance checks, and generate draft artifacts/diagrams locally or with configured cloud APIs.

Avoid When

You require a turnkey hosted SaaS with clear SLAs, strict compliance controls, or minimal setup; or you need authoritative legal determinations rather than informational/assistive outputs.

Use Cases

  • Search relevant patent regulations (MPEP, 35 USC, 37 CFR, EPC, PCT) with citations
  • Conduct prior art searches across large patent corpora using keyword/CPC/IPC or full-text queries
  • Review drafted claims for 35 USC 112(b) style issues (e.g., definiteness, antecedent basis)
  • Review specifications for 35 USC 112(a) adequacy (e.g., written description/enablement)
  • Run formalities checks aligned to MPEP 608
  • Generate patent-style diagrams (block diagrams, flowcharts, architectures)
  • Guide an end-to-end patent application drafting workflow for USPTO/EPO

Not For

  • Providing legal advice or acting as a substitute for a licensed patent attorney/agent
  • Guaranteeing patentability/allowance outcomes
  • Use where you cannot comply with third-party API/data usage terms (BigQuery dataset, EPO OPS, USPTO API)
  • Production deployments requiring a stable, well-specified public REST API with strong operational guarantees

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Google Cloud authentication via application-default login (gcloud auth application-default login) Environment-variable API credentials for EPO OPS (consumer key/secret) and optional external LLM providers (Anthropic/OpenAI keys)
OAuth: No Scopes: No

Authentication is largely configuration-based via environment variables and Google Cloud ADC for BigQuery. MCP tools appear to be used by the local client (Claude Code) after setup; no user-facing auth model (API keys, JWT, scopes) is described for the MCP server itself.

Pricing

Free tier: No
Requires CC: No

The repository itself is MIT licensed/open-source; external service costs depend on your cloud/API configuration.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • BigQuery access requires correct Google Cloud setup and billing/quota in your project; misconfiguration can fail searches.
  • Large downloads/index builds (e.g., MPEP PDFs ~500MB) can be slow and GPU-dependent; repeated setup/builds may be expensive in time.
  • Diagram generation and retrieval tools may depend on local Graphviz availability.
  • EPO OPS full-text support requires separate EPO API credentials and may fail if not configured.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Claude-Patent-Creator.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered