# MLflow Prompt Registry

> Use this tool when you need to streamline your prompt engineering workflow by accessing managed prompt templates directly within Claude Desktop. It solves problems of prompt discovery and variable substitution by providing a bridge between Claude and MLflow's Prompt Registry, allowing users to browse and retrieve templates with ease. The MLflow Prompt Registry MCP Server takes MLflow API inputs and outputs formatted prompt metadata and content according to the MCP specification.

Canonical page: https://skillsregistry.net/skills/b-step62-mlflow-prompt-registry  
JSON: https://api.skillsregistry.net/v1/skills/b-step62-mlflow-prompt-registry

## Description

MLflow Prompt Registry MCP Server provides a bridge between Claude Desktop and MLflow's Prompt Registry, enabling users to discover and use prompt templates managed in MLflow directly within Claude. Developed by B-Step62, this TypeScript implementation exposes two main tools: 'list-prompts' for browsing available templates and 'get-prompt' for retrieving and compiling specific prompts with variable substitution. The server connects to MLflow's API to fetch prompt metadata and content, then formats it according to the MCP specification. This integration is particularly valuable for teams already using MLflow for prompt management who want to streamline their prompt engineering workflow by accessing their templates directly in Claude Desktop.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/b-step62-mlflow-prompt-registry)
- **Repository:** <https://github.com/b-step62/mcp-server-mlflow>

## 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": "b-step62-mlflow-prompt-registry"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/b-step62-mlflow-prompt-registry` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/b-step62-mlflow-prompt-registry/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