mattpocock / mattpocock/evalite
Document how to evaluate MCP servers
Open
Nobody has claimed this yet.
documentation
enhancement
- Dominant language
- TypeScript
- Stars
- 1.7k
- Forks
- 102
- PR merge metrics
- No merged PRs in 30d
Description
Is there a way to test if a tool was called?
specifically, I am building my own MCP. I would like to test if AI actually uses my descriptions or not really...
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the repository's existing documentation and evaluation entry points for MCP-related workflows. Document how to verify that a tool was called and how to assess whether an AI used the tool descriptions, with completion defined by a clear, reproducible evaluation procedure.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai, documentation
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100