# Prompt Learning MCP Server

> Use this tool when you need to optimize and refine prompts for improved performance, and automate the process of retrieving high-performing examples. It solves problems related to prompt engineering, such as suboptimal query results and inefficient manual tuning, by providing stateful optimization and performance analytics. The tool takes in historical performance data and outputs refined prompts, high-performing examples, and trackable performance metrics.

Canonical page: https://skillsregistry.net/skills/curiositech-prompt-learning-mcp  
JSON: https://api.skillsregistry.net/v1/skills/curiositech-prompt-learning-mcp

## Description

Provides stateful prompt optimization using research-backed techniques like APE and OPRO, learning from historical performance data via a vector database. It enables users to automatically refine prompts, retrieve high-performing examples, and track performance analytics through iterative feedback.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-04-22

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gjlk1ewj47)
- **Repository:** <https://github.com/curiositech/prompt-learning-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "curiositech-prompt-learning-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/curiositech-prompt-learning-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/curiositech-prompt-learning-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt