← Registry

Developer Tools

patentprecheck.com

Provides tools to analyze source code or invention descriptions for patentability, including prior art search and legal guidance.

1 endpoint12 known toolsFirst detected June 21, 2026Last detected September 6, 2026

ENDPOINT 1

https://patentprecheck.com/mcp

No auth detected

MCP server metadata

Name
patent-precheck
Version
0.4.3
Capabilities
tools
Server instructions

Use precheck_score for pillar scores and band. precheck_prior_art, precheck_rejection_patterns, and precheck_legal_context add prosecution context. precheck_search_corpus is a fast corpus-only search; precheck_cpc_suggest is offline CPC hints. precheck_session_status and precheck_deliverables require report_id + session_key from a paid review. No API key required; analysis runs on the free tier by default.

Known tools 12

precheck_score

Run a patentability pre-check on source code or an invention description.

Inferred read-only
precheck_prior_art

Return the closest prior-art matches consulted for an invention (titles, sources, similarity scores, URLs).

Inferred read-only
precheck_rejection_patterns

Preview examination-risk signals: similar office-action rejections, abandonment patterns, and the primary statutory basis an examiner might cite (§101/§102/§103).

Inferred read-only
precheck_legal_context

Return a short snippet of current US software-patent legal guidance (CAFC, USPTO, Alice/§101) relevant to scoring this invention.

Inferred read-only
precheck_pillars

List the five patentability pillars (with statutes and weights) and the band rules used by precheck_score.

Inferred read-only
precheck_start_review

Return the URL where the user can start a paid (or promo-unlocked) Interactive Code Review that strengthens each pillar with evidence and produces a filing package.

Inferred read-only
precheck_search_corpus

Fast semantic search against the 2M+ prior-art corpus without LLM scoring.

Inferred read-only
precheck_cpc_suggest

Suggest Cooperative Patent Classification (CPC) codes for an invention description.

Inferred read-only
precheck_session_status

Return status for an active Interactive Code Review session.

Inferred read-only
precheck_deliverables

Return download URLs for finalized ICR deliverables (filing packet, coaching report, package zip, scorecard PDF).

Inferred read-only
precheck_lookup_patent

Resolve a US patent or application number (e.g.

Inferred read-only
precheck_compare_to_patent

Compare invention text to a known US patent: embedding similarity plus prior-art risk analysis (statute hints, overlap theme, distinction checklist).

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.patent-precheck]
url = "https://patentprecheck.com/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "patent-precheck": {
      "type": "http",
      "url": "https://patentprecheck.com/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: patent-precheck
Remote MCP URL: https://patentprecheck.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "patent-precheck": {
      "url": "https://patentprecheck.com/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "patent-precheck": {
      "type": "http",
      "url": "https://patentprecheck.com/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "patent-precheck",
  "transport": "streamable-http",
  "url": "https://patentprecheck.com/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for patentprecheck.com was fetched 2026-09-07T10:15:13.148Z.

Trust status Trusted

patentprecheck.com is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.