What is patent_mcp_server AGENTS.md?

Contribution instructions for Patent MCP Server, a service that connects tools to patent-related data. They explain which project documents to read and how to handle issues, pull requests, and common project patterns.

Use them when filing an issue, preparing a pull request, debugging client requests, or changing the server according to its documented conventions.

They reduce mistakes by making project conventions and useful debugging information clear before changes or reports are made.

How riemannzeta/patent_mcp_server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to riemannzeta/patent_mcp_server. 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/riemannzeta/patent_mcp_server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/riemannzeta/patent_mcp_server

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/riemannzeta/patent_mcp_server/agents-md/github.svg)](https://agentmods.dev/instructions/riemannzeta/patent_mcp_server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/riemannzeta/patent_mcp_server/agents-md"><img src="https://agentmods.dev/badge/instructions/riemannzeta/patent_mcp_server/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/riemannzeta/patent_mcp_server/agents-md"><img src="https://agentmods.dev/badge/instructions/riemannzeta/patent_mcp_server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,083 This file is loaded in full into every session.

When invoked 1,083 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.

Model	Per session	Once invoked
Fable 5.1	$0.01083	$0.01083
Opus 5	$0.00541	$0.00541
Sonnet 5	$0.00217	$0.00217
Haiku 4.5	$0.00108	$0.00108

Measured 9d ago against content hash 54d32775cf99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

patent_mcp_server 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 9d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents (Claude, GPT-class, Cursor, Aider, etc.) contributing issues, PRs, or code review to patent-mcp-server.

This file complements CONTRIBUTING.md, which applies to all contributors. Read both.

Read CLAUDE.md first

CLAUDE.md is the authoritative source for project conventions: release workflow, tool naming, error handling, the decommissioned-API pattern, and the rule that all unit tests must pass before any commit. An agent that hasn't read CLAUDE.md will get patterns subtly wrong — read it before making changes.

When filing an issue

Use the bug-report or feature-request template (.github/ISSUE_TEMPLATE/). Both are YAML forms — fill in every required field.

The single highest-value thing you can include is the constructed request the client made, captured from LOG_LEVEL=DEBUG. Many "the tool returns wrong results" reports turn out to be either user-side query syntax or upstream USPTO API quirks; the logged URL and body settle it instantly.

If you don't have access to live logs (for example, the user reported the bug to you secondhand), say so explicitly in the report — write "constructed request not captured" rather than guessing or omitting. A report that admits a gap is more useful than one that papers over it.

Don't file an issue for a tool that returns API_UNAVAILABLE — those are intentional and documented. Check check_api_status first.

When submitting a PR

In order:

Confirm the bug exists. Reproduce it locally — either via uv run pytest -m integration or by writing a one-off async script that hits the affected tool. A PR without reproduction is a guess.
Identify the root cause. Don't pattern-match a fix to surface symptoms. If a query parameter is being ignored, find why — wrong default, dropped param, upstream API requiring a different shape, etc.
Write a unit test that fails before the fix and passes after. This is the contract that prevents regression.
Make the smallest fix that addresses the root cause. Don't refactor adjacent code in the same PR unless it's necessary for the fix.
Run the full test suite. uv run pytest — must be 100% green.
Bump the version if the change is user-visible. Patch in both pyproject.toml and config.py:USER_AGENT.
Update docstrings. The Args: and USE THIS TOOL WHEN: sections in tool definitions are surfaced to other LLMs as the tool's interface — they matter as much as the code.

Read the full file on GitHub · 66 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.

9d ago First seen · 66 lines · 1,083 tokens per session scan A 54d32775cf99

Subscribe to this mod's changes

patent_mcp_server AGENTS.md is an instructions file published in the GitHub repository riemannzeta/patent_mcp_server (78 stars, last pushed 7d ago), licensed MIT. It adds 1,083 tokens to every session, about $0.0054 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 2026-08-30.

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

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 · 5,153 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

patent_mcp_server: Instructions file for Codex