Le catalogue réel des outils pour IA

A standardized testing harness for MCP servers and agent workflows

Evaluate one public URL for WebMCP readiness: intent, tools observed, recommended, do-not-expose.

Evaluate a+b style arithmetic. Expression discarded.

Run up to 25 Apify Actors in order in one call, passing each step's dataset to the next.

Regression checks for Japanese order automations: six free cases, strict JSON scoring and CI gates.

Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.

Local test execution and coverage summaries for onboarding agents.

Self-hosted MCP for controlled AI development and staging without a general-purpose remote shell.

Cloudflare Workers MCP server: ai-eval

FastAPI-native Model Context Protocol framework and stdio runner.

Rights-aware censorship, China-economic status, and tamper-evident AI evaluation tools.

Stockfish chess eval: best move, score, principal variation, multipv. $0.005/call via x402.

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

Code Runner MCP Server which can run code in various programming languages.

JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.

Remote MCP for Gemini upgrade evals, prompt regressions, output diffs, and eval receipts.

Author verifiable eval records through a draft→review→revise→submit loop with enforced graders.

Revit model query + APS Design Automation runner.

Wraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.

Windows-only headless LLM task automation engine with scheduling via Windows Task Scheduler.