Natural language testing for Model Context Protocol servers. Deterministic, open source, funded by LoopIQ.
Natural-language testing for Model Context Protocol servers.
Visual QA workspace · English ⇄ YAML parity · interactive evidence timeline · CLI, CI, and shareable reports — watch the MP4
MCP Rigor lets QA teams test MCP tools, resources, prompts, contracts, and transports without writing test code. Tests are deterministic: no AI model interprets the wording.
Status: 1.5.0 stable. Node.js 20 or 22 is required.
MCP Rigor is published on npm as mcprigor. The package ships compiled code, ready to run:
Use npx mcprigor in commands below, or install globally (npm install -g mcprigor) to use mcprigor directly. In a project where tests run only during development or CI, npm install --save-dev mcprigor keeps it out of production dependencies.
Only needed if you want to modify MCP Rigor itself:
Or expose MCP Rigor to AI coding agents as an MCP server (docs):
Open the printed http://127.0.0.1:... URL. You can select a suite, edit it, validate the wording, run tests, run transport parity, and review results.
The workspace is loopback-only and does not accept arbitrary commands from the browser.
Do not place reusable credentials directly in test files.
See the natural-language cookbook for copy-ready examples.
MCP Rigor runs every scenario against both targets and reports semantic differences.
Provide a small .mcpr file containing the target, then run:
The guided author discovers operations, asks for inputs, previews a response, and writes a reviewable natural-language test.
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/FusionOnePlatform--mcprigor.html)
Standalone Go runner and @9l/playwright SDK for bounded Playwright execution with validated receipts.
illiahaidar/mcptrustcheckerMCP security scanner — offline, deterministic A–F Trust Score for Model Context Protocol servers. Detects tool poisoning, prompt injection & toxic flows.
doeixd/foldkit-plusA Schema-first agent layer for Foldkit: project an application's Model and Message union into one contract, then expose it through WebMCP, MCP, or in-app agents.
KonghuanSmart/calculate-mcpA high-precision calculation & binary data MCP server with chained batch execution (batch_calc), bitwise logic, IEEE 754, crypto, and math.
sanjayrohith/DejavuRepository-scoped memory for coding agent's decisions, pitfalls, and handoffs stored in one inspectable SQLite file, so agents continue instead of starting over.
fdhhhdjd/MCP-STARTER-KITBuild a secure, production-ready MCP server for any project — connect Claude, ChatGPT & any AI agent to your backend with a URL + API key. Streamable HTTP + stdio + OAuth 2.0 (PKCE).
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.