io.github.lazymac2x/ai-eval

Official3 toolsLive

by lazymac2x

Cloudflare Workers MCP server: ai-eval

io.github.lazymac2x/ai-eval — Cloudflare Workers MCP Server

Cloudflare Workers MCP server “ai-eval” provides access to a REST API alongside MCP using JSON-RPC 2.0. The live endpoint is listed as api.lazy-mac.com/ai-eval, and the server package is identified by the slug io.github.lazymac2x/ai-eval. It exposes 3 tools.

🛠️ Key Features

Cloudflare Workers MCP server
ai-eval
REST + MCP (JSON-RPC 2.0)
Live at api.lazy-mac.com/ai-eval

🚀 Use Cases

Integrate the “ai-eval” functionality via MCP
Use REST-based access for the same service

⚡ Developer Benefits

JSON-RPC 2.0 MCP compatibility
MCP plus REST access model

⚠️ Limitations

Tool coverage is limited to 3 tools (per toolCount)

Captured live from the server via tools/list.

score_response

Score an AI response against a prompt using heuristic metrics (length, relevance, structure, completeness)

Parameters3

prompt	string	required	The original prompt/question
response	string	required	The AI response to evaluate
criteria	array	optional	Optional keywords that should appear in response

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "The original prompt/question"
    },
    "response": {
      "type": "string",
      "description": "The AI response to evaluate"
    },
    "criteria": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional keywords that should appear in response"
    }
  },
  "required": [
    "prompt",
    "response"
  ]
}

compare_responses

Compare and rank multiple AI responses to the same prompt

Parameters2

prompt	string	required
responses	array	required

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string"
    },
    "responses": {
      "type": "array",
      "minItems": 2,
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "prompt",
    "responses"
  ]
}

text_metrics

Get text quality metrics: word count, sentence count, estimated tokens, readability grade

Parameters1

text

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    }
  },
  "required": [
    "text"
  ]
}

Install

Tools (3)

score_responsecompare_responsestext_metrics

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://api.lazy-mac.com/ai-eval/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "ai-eval": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.lazy-mac.com/ai-eval/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.lazymac2x/ai-eval

io.github.lazymac2x/ai-eval — Cloudflare Workers MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

score_response

compare_responses

text_metrics

ai-eval-api

Install

Remote endpoint

Related servers