MCP Server
MCP
CompletionKit
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Configuration Example
{
"remotes": [
{
"type": "streamable-http",
"url": "https://completionkit.com/mcp",
"headers": [
{
"description": "Your CompletionKit API token as: Bearer <token>. Create one under Settings > API tokens.",
"isRequired": true,
"isSecret": true,
"name": "Authorization"
}
]
}
],
"packages": []
}
mcp
model-context-protocol
streamable-http
By
Comments
Sign in to leave a comment