Borrowing it
Nothing to install: this file belongs to anirbanbasu/pymcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anirbanbasu/pymcp/master/AGENTS.mdgit clone --depth 1 https://github.com/anirbanbasu/pymcpWrote 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.
[](https://agentmods.dev/instructions/anirbanbasu/pymcp/agents-md)<a href="https://agentmods.dev/instructions/anirbanbasu/pymcp/agents-md"><img src="https://agentmods.dev/badge/instructions/anirbanbasu/pymcp/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.
<a href="https://agentmods.dev/instructions/anirbanbasu/pymcp/agents-md"><img src="https://agentmods.dev/badge/instructions/anirbanbasu/pymcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01467 | $0.01467 |
| Opus 5.5 | $0.00587 | $0.00587 |
| Sonnet 5.5 | $0.00293 | $0.00293 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
pymcp 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This file provides guidance to coding agents (Claude Code, Codex, and similar tools) when working with code in this repository.
Project
pymcp: a template repository for building MCP servers with FastMCP in Python. It is not itself an application with a fixed domain — the greet, generate_password, text_web_search, permutations, and run_python_code tools exist to demonstrate patterns (tool/resource/prompt registration, middleware, caching, response metadata), not because they're the point of the project. When adapting this repository into a new MCP server, expect to delete the example tools/resources/prompts and replace them, while keeping the surrounding scaffolding (mixin registration, middleware, env var handling, test layering) intact.
Commands
uv manages the Python 3.12 environment — do not use pip directly. Commands run either via plain uv run or the justfile (just -l lists every recipe).
just install # sync minimal (runtime-only) dependencies
just install-all # sync all dependency groups (dev, test)
just format # ruff format + ruff check --fix
just type-check # uv run ty check
just test-coverage # pytest (via coverage) across tests/, then coverage report
just launch-inspector # run the MCP Inspector against the server (needs nvm/node)
just vulnerability-scan # osv-scanner over the source tree
just install-pre-commit-hooks / just pre-commit-update # manage hooks via `prek`, not `pre-commit`
Run a single test:
uv run pytest tests/test_server.py::TestMCPServer::test_greet_default -v
just test-coverage enforces fail_under = 100 (see [tool.coverage.report] in pyproject.toml); use # pragma: no cover for genuinely unreachable branches rather than writing tests around them. Running a single test with plain pytest/uv run pytest skips the coverage gate, which is expected during iterative development.
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.
- 1mo ago First seen · 65 lines · 1,467 tokens per session scan A 9e8ec8609c8e
pymcp AGENTS.md is an instructions file published in the GitHub repository anirbanbasu/pymcp (8 stars, last pushed 9d ago), licensed MIT. It adds 1,467 tokens to every session, about $0.0059 per session on Opus 5.5. 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 2026-09-15.
pymcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pymcp AGENTS.mdanirbanbasu/pymcp | Instructions file | 8 | 9d ago | MIT | A | 1,467 | Codex, OpenCode |
| graftcode graftcode-python.instructions.mdgrft-dev/graftcode | Instructions file | 967 | 1mo ago | none | A | 4,639 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |