mcp-fetch-patents: Instructions file for Codex

AGENTS.md

mcp-fetch-patents AGENTS.md is an instructions file for Codex, OpenCode from clankercode/mcp-fetch-patents. It costs 1,272 tokens per session, scanned A, original, CC0-1.0.

Project instructions for mcp-fetch-patents, a server that fetches, caches, and searches patent information in Python and Rust.

In plain words
What is it for?
Build, test, lint, and serve the Python or Rust implementations, including their MCP and local HTTP interfaces.
Why use it?
They give the coding agent the project’s layout, commands, testing rules, and coding conventions so changes fit the existing codebase.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is clankercode/mcp-fetch-patents's own configuration. It tells Codex and OpenCode how to work on mcp-fetch-patents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-fetch-patents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to clankercode/mcp-fetch-patents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/clankercode/mcp-fetch-patents/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/clankercode/mcp-fetch-patents

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-fetch-patents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/clankercode/mcp-fetch-patents/agents-md.svg)](https://agentmods.dev/instructions/clankercode/mcp-fetch-patents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/clankercode/mcp-fetch-patents/agents-md"><img src="https://agentmods.dev/badge/instructions/clankercode/mcp-fetch-patents/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,272 This file is loaded in full into every session.
When invoked 1,272 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01272 $0.01272
Opus 5 $0.00636 $0.00636
Sonnet 5 $0.00254 $0.00254
Haiku 4.5 $0.00127 $0.00127

Measured 7d ago against content hash f4b96d945d10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-fetch-patents AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — mcp-fetch-patents

Project Overview

Dual-implementation MCP server for patent fetching, caching, and search.

  • Python (src/python/) — reference implementation
  • Rust (src/rust/) — production implementation, feature parity with Python

Both expose MCP tools over stdio JSON-RPC. Rust and the Python entrypoints also expose localhost HTTP at /mcp via serve-http; the shared guarantee is the default URL, not wire-identical HTTP behavior across implementations.

Build & Test Commands

Must use CC=gcc for all cargo commands (default cc is a wrapper that breaks aws-lc-sys).

just test-rust              # Run all Rust tests (237 tests)
just build-rust             # Debug build
just build-rust-release     # Release build
just check-rust             # Quick type-check
just lint-rust              # Clippy with -D warnings
just test                   # Python fast tests
just ci                     # Python fast + Rust tests
just serve-rust             # Run Rust MCP server
just serve-rust-http        # Run Rust MCP server over localhost HTTP
just serve-http             # Run Python fetch MCP server over localhost HTTP
just serve-search-http      # Run Python search MCP server over localhost HTTP
just install-rs

For direct cargo commands:

CC=gcc cargo test --manifest-path src/rust/Cargo.toml
CC=gcc cargo build --manifest-path src/rust/Cargo.toml

After you have completed a your tasks, commit your work and run 'just install-rs'.

Rust Module Layout

src/rust/src/
  lib.rs              — crate root, pub mod declarations
  main.rs             — binary entrypoint
  config/mod.rs       — PatentConfig (env vars, .patentrc)
  id_canon/           — patent ID canonicalization
  cache/              — SQLite-backed patent cache
  fetchers/           — HTTP fetch backends (USPTO, EPO, Google)
    http/             — HTTP fetcher implementations (per-source files)
    browser.rs        — Playwright/chromiumoxide browser fetcher
    web_search/       — web search utilities
    mod.rs            — FetcherOrchestrator, PatentSource trait
  converters/         — format conversion (XML, JSON, etc.)
  journal.rs          — activity journal
  planner.rs          — NL query planner (deterministic, rule-based)
  ranking.rs          — PatentHit scoring/reranking
  search/             — search MCP tools
    mod.rs            — module root, SearchBackends struct
    orchestrator.rs   — search orchestration (NL search + enrichment)
    session_manager.rs — session persistence (atomic JSON, path traversal guard)
    searchers/        — search backends
      mod.rs          — re-exports, shared helpers
      serpapi.rs      — SerpAPI Google Patents backend
      uspto.rs        — USPTO text search backend
      epo_ops.rs      — EPO OPS backend (OAuth, citations, family, XML/JSON)
    profile_manager.rs — browser profile dirs with file-based locking
    browser_search.rs  — Google Patents via chromiumoxide
  server/mod.rs       — MCP server: tool descriptors + handlers (fetch + search)

Read the full file on GitHub · 122 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 122 lines · 1,272 tokens per session scan A f4b96d945d10

Subscribe to this mod's changes

mcp-fetch-patents AGENTS.md is an instructions file published in the GitHub repository clankercode/mcp-fetch-patents (2 stars, last pushed 2mo ago), licensed CC0-1.0. It adds 1,272 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens