MCPgee
MCPgee
MCPgeeMCPgee

Marmot

v1.0.0•Data Science & ML•stable

The open-source context layer for your AI. Catalog your tables, topics, queues and APIs then expose real metadata to your AI agents.

bigdatadata-catalogdata-collaborationdata-discoverydata-exploration
Share:
571
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Marmot?

Marmot is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open-source context layer for your ai. catalog your tables, topics, queues and apis then expose real metadata to your ai agents.

The open-source context layer for your AI. Catalog your tables, topics, queues and APIs then expose real metadata to your AI agents.

This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The open-source context layer for your AI. Catalog your tabl

Use Cases

Catalog databases, topics, queues, and APIs with real metadata exposure.
Enable AI agents to discover and understand data assets across your organization.
marmotdata

Maintainer

LicenseMIT
Languagego
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx marmot

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Marmot

Marmot is an open-source data catalog that serves as a context layer for AI agents, exposing real metadata about your organization's tables, topics, queues, and APIs through the Model Context Protocol. Instead of hallucinating schema details, AI agents can query Marmot's three MCP tools to discover data assets by natural language, look up ownership, and resolve business glossary terms against actual certified metadata. It is designed for data teams that want their AI tooling to make informed decisions based on live data catalog information rather than guesswork.

Prerequisites

  • A running Marmot instance (self-hosted via Docker, Helm, or binary, or cloud-hosted)
  • A Marmot API key (generated from your profile under Settings > API Keys)
  • Node.js and npx available to run the mcp-remote bridge package
  • An MCP-compatible client such as Claude Desktop, Claude Code, or Cursor
1

Deploy a Marmot instance

If you do not already have Marmot running, deploy it using Docker, Helm, or the standalone binary following the official Deploy documentation at marmotdata.io/docs/Deploy.

2

Generate a Marmot API key

Log into your Marmot instance, navigate to your Profile, then Settings > API Keys, and create a new API key. Copy this key — you will need it in the MCP client configuration.

3

Catalog your data assets

Use the Marmot UI or CLI to register your databases, Kafka topics, message queues, and API definitions. The richer your catalog, the more value AI agents can extract from it.

4

Configure your MCP client

Edit your claude_desktop_config.json to point to your Marmot instance using the mcp-remote package as a bridge. Replace the server URL and API key placeholders with your actual values.

5

Verify the three MCP tools are available

After restarting your MCP client, confirm that the discover_data, find_ownership, and lookup_term tools appear and can be invoked. Test by asking the AI to find a data asset by name.

Marmot Examples

Client configuration

Add this block to your claude_desktop_config.json. The mcp-remote package bridges HTTP-based MCP servers to the stdio transport. Add --allow-http if your Marmot instance uses plain HTTP during development.

{
  "mcpServers": {
    "marmot": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://<your-marmot-server>/api/v1/mcp",
        "--header",
        "X-API-Key:<your-api-key>"
      ]
    }
  }
}

Prompts to try

Use these prompts to explore your organization's data catalog through your AI assistant.

- "Find all tables related to customer orders in our data catalog."
- "Who owns the payments Kafka topic and what does it contain?"
- "What does the term 'churn rate' mean in our business glossary?"
- "List all data assets owned by the data-engineering team."

Troubleshooting Marmot

403 Forbidden when MCP tools are called

Check that your X-API-Key header value is correct and that the API key has not been revoked. Regenerate the key from Marmot Profile > Settings > API Keys if needed.

mcp-remote fails to connect to the Marmot server

If your instance uses HTTP rather than HTTPS, add --allow-http to the args array. Also verify that the /api/v1/mcp endpoint is reachable from your machine with a curl request.

discover_data returns no results

Ensure that data assets have been cataloged in your Marmot instance. The tool searches existing catalog entries; an empty catalog will yield no results. Check the Marmot UI to confirm assets are registered.

Frequently Asked Questions about Marmot

What is Marmot?

Marmot is a Model Context Protocol (MCP) server that open-source context layer for your ai. catalog your tables, topics, queues and apis then expose real metadata to your ai agents. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Marmot?

Follow the installation instructions on the Marmot GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Marmot?

Marmot works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Marmot free to use?

Yes, Marmot is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Marmot Alternatives — Similar Data Science & ML Servers

Looking for alternatives to Marmot? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Data Science & MLBrowse All Servers

Quick Config Preview

{ "mcpServers": { "marmot": { "command": "npx", "args": ["-y", "marmot"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Marmot?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides