MLflow Prompt Registry

by b-step62

1 stars

224 downloads

Not rated

GitHub

About

Bridges MLflow's Prompt Registry with Claude Desktop, enabling direct discovery and use of managed prompt templates with variable substitution capabilities.

Details

Author: b-step62
Repository: B-Step62/mcp-server-mlflow
GitHub stars: 1
Downloads: 224
Categories: Developer Tools, AI, Productivity, Workplace, Search, Communication, API, Infrastructure, Other
Tags: #integration

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name MLflow Prompt Registry

Command (node, npx, python, etc.) node
Arguments
- Argument 1 <absolute-path-to-this-repository>/dist/index.js
Environment
- MLFLOW_TRACKING_URI http://localhost:5000
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

JSON

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

From the repository

1 Install Mlflow And Start Prompt Registry

Install and start an MLflow server if you haven't already to host the Prompt Registry:

pip install mlflow>=2.21.1 mlflow server --port 5000

If you haven't already, create a prompt template in MLflow following](https://github.com/anthropics/ModelContextProtocol/blob/main/docs/prompts.md)this guide.

Configure Claude for Desktop by editingclaude_desktop_config.json:

{ "mcpServers": { "mlflow": { "command": "node", "args": ["<absolute-path-to-this-repository>/dist/index.js"], "env": { "MLFLOW_TRACKING_URI": "http://localhost:5000" } } } }

Make sure to replace theMLFLOW_TRACKING_URIwith your actual MLflow server address.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

next-devtools-mcp is a MCP server that provides Next.js development tools and utilities for AI coding assistants like Claude and Cursor.

Word search, crossword, and sudoku generator MCP server with printable PDF worksheets, themed word banks, and verifiable LLM evals. Local-first, from the makers of puzzletide.com.

A demonstration server for ActionKit, providing access to Slack actions via Claude Desktop.

MCP server that lets Claude Code agents delegate tasks to agents in other project directories, with parallel dispatch, sessions, and async jobs.

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

A Python MCP package that gives your LLM agents complete file system and shell capabilities — production-ready, sandboxed, and wired to any LLM in minutes.

Integrates with Google AI Studio/Gemini API for PDF to Markdown conversion and content generation.

Anchor Browser (https://anchorbrowser.io) is secure infrastructure for computer-use agents — stealth cloud browsers, authentication, captcha bypass, and a hosted MCP server for Cursor, Claude, and Windsurf.

`list-prompts`

List available prompts. Inputs: cursor (optional string for pagination), filter (optional string to filter prompts). Returns a list of prompt objects.

`get-prompt`

Retrieve and compile a specific prompt. Inputs: name (string for the name of the prompt), arguments (optional object with prompt variables). Returns a compiled prompt object.

- list-prompts
- List available prompts
- Inputs:
- cursor (optional string): Cursor for pagination
- filter (optional string): Filter for prompts
- Returns: List of prompt objects
- get-prompt
- Retrieve and compile a specific prompt
- Inputs:
- name (string): Name of the prompt to retrieve
- arguments (optional object): JSON object with prompt variables
- Returns: Compiled prompt object

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mlflow prompt registry": {
            "env": {
                "MLFLOW_TRACKING_URI": "http://localhost:5000"
            },
            "args": [
                "<absolute-path-to-this-repository>/dist/index.js"
            ],
            "command": "node"
        }
    }
}

Linux

{
    "env": {
        "MLFLOW_TRACKING_URI": "http://localhost:5000"
    },
    "args": [
        "<absolute-path-to-this-repository>/dist/index.js"
    ],
    "command": "node"
}

Macos

{
    "env": {
        "MLFLOW_TRACKING_URI": "http://localhost:5000"
    },
    "args": [
        "<absolute-path-to-this-repository>/dist/index.js"
    ],
    "command": "node"
}

Windows

{
    "env": {
        "MLFLOW_TRACKING_URI": "http://localhost:5000"
    },
    "args": [
        "<absolute-path-to-this-repository>/dist/index.js"
    ],
    "command": "node"
}

Access prompt templates managed in an MLflow Prompt Registry. Requires a running MLflow server configured via the MLFLOW_TRACKING_URI environment variable.

Model Context Protocol (MCP) Server forMLflow Prompt Registry, enabling access to prompt templates managed in MLflow.

This server implements the MCP Prompts specificationfor discovering and using prompt templates from MLflow Prompt Registry. The primary use case is to load prompt templates from MLflow in Claude Desktop, allowing users to instruct Claude conveniently for repetitive tasks or common workflows.

- list-prompts

- List available prompts
- Inputs:

- cursor(optional string): Cursor for pagination
- filter(optional string): Filter for prompts

- Retrieve and compile a specific prompt
- Inputs:

- name(string): Name of the prompt to retrieve
- arguments(optional object): JSON object with prompt variables

1: Install MLflow and Start Prompt Registry

Install and start an MLflow server if you haven't already to host the Prompt Registry:

pip install mlflow>=2.21.1 mlflow server --port 5000

If you haven't already, create a prompt template in MLflow following this guide.

Configure Claude for Desktop by editingclaude_desktop_config.json:

{ "mcpServers": { "mlflow": { "command": "node", "args": ["<absolute-path-to-this-repository>/dist/index.js"], "env": { "MLFLOW_TRACKING_URI": "http://localhost:5000" } } } }