retriEVAL runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 27 Aug 2026.
LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.
What the code does
We read the source, 22 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
document.getElementById("runsNav").innerHTML = RUNS.map(function(r){
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to retriEVAL
same job, measured the same wayMCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Hallucination validator and factual grounding checker for LLM outputs.
MCP server for real-time LLM API documentation — stop hallucinations
Detect fabrication and hallucination in any LLM output. 30+ models supported.
Fact-check and fix AI outputs. Hallucination detection, schema validation, auto-repair.
Hallucination & safety checks for LLM/Agent outputs: claim-level fact-check with citations.
Wraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.
retriEVAL — questions
Answers built from our own checks of this server.