CompletionKit for Cursor
com.completionkit/evals
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
client:Cursor
transport:streamable-http
tools:54
Install CompletionKit in Cursor
~/.cursor/mcp.json · windows: %USERPROFILE%\.cursor\mcp.json
{
"mcpServers": {
"evals": {
"url": "https://completionkit.com/mcp"
}
}
}Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs
What Cursor can do once it is connected
- prompts_list
- prompts_get
- prompts_create
- prompts_update
- prompts_delete
- prompts_publish
- prompts_suggest_improvement
- runs_list
- runs_get
- runs_create
- runs_update
- runs_delete
- runs_generate
- runs_regrade
- runs_rerun
- runs_retry_failures
- responses_list
- responses_get
- datasets_list
- datasets_get
- datasets_create
- datasets_update
- datasets_delete
- datasets_create_from_url