A zero-dependency CLI that validates and grades an MCP server's resources and prompts primitives A to F over stdio, filling the gap left by the tool-only checkers and slotting in as a ninth mcp-scorec
View on GitHub ↗Validate and grade an MCP server's resources and prompts primitives, A to F, over the stdio transport.
The Model Context Protocol has three primitives: tools, resources, and prompts. Most tooling only ever looks at tools. This CLI is for the other two. It launches your MCP server, exercises its resource and prompt surface, and reports a graded scorecard you can gate a CI pipeline on.
- Zero dependencies (Python standard library only, 3.9+) - Grades four dimensions: resource hygiene, prompt hygiene, capability consistency, error correctness - Output as console, JSON, Markdown, or a shields.io badge - --min-grade gate for CI (non-zero exit on failure) - Ships a healthy sample server (grades A) and a broken one (grades F) so you can try it immediately
Point it at your own server (anything launched over stdio):
Resource hygiene - Each listed resource has a name and a uri with a valid scheme - mimeType is present and well-formed (recommended) - Advertised URI templates are valid RFC 6570 - resources/read on each listed resource returns contents whose uri matches and that carry a text or blob body
Prompt hygiene - Each prompt has a name and well-formed argument definitions - prompts/get with all required arguments supplied returns a valid messages array with proper roles - The rendered prompt has no leftover {{placeholder}} or {arg} tokens
Capability consistency - A server that serves resources or prompts also declares the matching capability (and vice versa) - If resources.subscribe is advertised, a resources/subscribe call actually works - The server writes only JSON to s
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/shriramkv--mcp-prompts-resources.html)
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
zhuyansen/new-term-radarDaily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
yzg1226/mcd-party-officer🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
fellowgeek/mcp-memoryAn OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
hirotomasato/yowesGenerate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.
hujjun/mcd-saver-strategist麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.