MCPM is an open-source command-line package manager and registry for MCP servers, which provide AI clients with additional tools or context. It lets users find, install, organize, run, update, and connect servers to clients such as Claude Desktop, Cursor, and Windsurf.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/pathintegral-institute/mcpm.shWrote 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/rules/pathintegral-institute/mcpm.sh/pytest)<a href="https://agentmods.dev/rules/pathintegral-institute/mcpm.sh/pytest"><img src="https://agentmods.dev/badge/rules/pathintegral-institute/mcpm.sh/pytest/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/rules/pathintegral-institute/mcpm.sh/pytest"><img src="https://agentmods.dev/badge/rules/pathintegral-institute/mcpm.sh/pytest.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 | $0.00039 | $0.00039 |
| Opus 5.5 | $0.00016 | $0.00016 |
| Sonnet 5.5 | $0.00008 | $0.00008 |
| Haiku 4.5 | $0.00004 | $0.00004 |
Grade A, and why
pytest 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.
What it actually says
always run pytest at the end of a major change always run ruff lint at then end of any code 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.
- 1mo ago First seen · 7 lines · 39 tokens per session scan A a31f0ba4cc76
pytest is a cursor rule published in the GitHub repository pathintegral-institute/mcpm.sh (1,014 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session, about $0.0002 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 2026-08-30.
Other cursor rules, from other repositories
swamr-qa-loop
Swamr QA Loop — validates every task output through automated and manual checks. Invoked automatically by the orchestrator after each task completion. Enforces quality gates with evidence-based pass/fail decisions.
cursorrules
You are a senior TypeScript developer. Always use strict mode. Prefer functional patterns. Run prettier on save. Never edit dist/ or nodemodules/. Use vitest for testing. Prefer named exports.
testing
Testing: test design, mocking strategy, coverage philosophy.
jest
Jest: describe/it, matchers, mocking, async testing.
playwright
Playwright: e2e testing, page objects, fixtures, assertions.
vitest
Vitest: unit testing, mocking, coverage, snapshot testing.