Prompt Auto-Optimizer MCP

MIT License

Overview InspectNew Schema Related Servers Reviews Score

gepa_evaluate_prompt

Assess prompt performance across multiple tasks using parallel evaluations and iterative rollouts to optimize AI prompt effectiveness and reliability.

Instructions

Evaluate prompt candidate performance across multiple tasks

Input Schema

Name	Required	Description
`parallel`	No	Whether to run evaluations in parallel
`promptId`	Yes	Unique identifier for the prompt to evaluate
`rolloutCount`	No	Number of evaluation rollouts per task
`taskIds`	Yes	List of task IDs to evaluate the prompt against

Input Schema (JSON Schema)

{
  "properties": {
    "parallel": {
      "default": true,
      "description": "Whether to run evaluations in parallel",
      "type": "boolean"
    },
    "promptId": {
      "description": "Unique identifier for the prompt to evaluate",
      "type": "string"
    },
    "rolloutCount": {
      "default": 5,
      "description": "Number of evaluation rollouts per task",
      "type": "number"
    },
    "taskIds": {
      "description": "List of task IDs to evaluate the prompt against",
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "promptId",
    "taskIds"
  ],
  "type": "object"
}

Install Server

HTTP connection URL

Other Tools from Prompt Auto-Optimizer MCP

Related Tools

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sloth-wq/prompt-auto-optimizer-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server