Cloudflare Workers MCP server: ai-eval
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Compare and rank multiple AI responses to the same prompt
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Compare and rank multiple AI responses to the same prompt
| Argument | Type | Description |
|---|---|---|
| prompt* | string | |
| responses* | array |
{
"type": "object",
"required": [
"prompt",
"responses"
],
"properties": {
"prompt": {
"type": "string"
},
"responses": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 2
}
}
}Score an AI response against a prompt using heuristic metrics (length, relevance, structure, completeness)
| Argument | Type | Description |
|---|---|---|
| prompt* | string | The original prompt/question |
| criteria | array | Optional keywords that should appear in response |
| response* | string | The AI response to evaluate |
{
"type": "object",
"required": [
"prompt",
"response"
],
"properties": {
"prompt": {
"type": "string",
"description": "The original prompt/question"
},
"criteria": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional keywords that should appear in response"
},
"response": {
"type": "string",
"description": "The AI response to evaluate"
}
}
}Get text quality metrics: word count, sentence count, estimated tokens, readability grade
| Argument | Type | Description |
|---|---|---|
| text* | string |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string"
}
}
}