Help
Getting Started
Scan your first server
Run a competitive scan to see how your MCP server tool descriptions compare against named rivals in your category.
Read the leaderboard
See which servers win in each category and why — browse pick-rates, description smells, and verified rewrites.
Set up monitoring
Get alerted when model releases or rival schema changes shift your pick-rate by more than 5 points.
FAQ
What is pick-rate?
The percentage of tasks where an AI agent chooses your MCP server’s tool over a named rival’s equivalent tool.
How are scans run?
We run 25 realistic tasks per category through Claude, presenting your tool descriptions alongside your rival’s. The model picks one — we count wins.
What are smells?
Description defects (based on arXiv 2602.14878) that cause models to skip your tool. Common examples: no stated purpose, ambiguous scope, missing parameters.
How do verified rewrites work?
We propose a description fix, re-run the 25-task sim, and only accept rewrites that measurably lift your pick-rate. Regressions are rejected.
What triggers a monitoring alert?
A new model release or a rival schema change that causes a ≥5 pt drop in your pick-rate.