MCP Server

Active

MIT

Marmot Data Catalog MCP Server

io.github.marmotdata/marmot

Open-source data catalog for AI agents—search assets, explore lineage, and expose certified metadata through MCP.

What is the Marmot Data Catalog MCP server?

The Marmot Data Catalog MCP server is an open-source data catalog that exposes certified metadata about your data assets (tables, topics, queues, APIs, dashboards) to AI agents through the Model Context Protocol. It enables AI tools to search, discover, and understand data lineage and ownership without requiring complex enterprise infrastructure.

Marmot is a lightweight, single-binary data catalog designed for teams who need powerful data discovery without enterprise complexity. It catalogs all your data assets, enriches them with context like ownership and business documentation, and makes that metadata accessible to both your team and AI agents via MCP. Use it to help AI tools understand your data landscape and make informed decisions based on real metadata.

How to install Marmot Data Catalog

Copy-paste configuration for popular MCP clients.

transport: http

Config generated by PluginBench — verify against the source before use.

Environment / auth

X-API-Key
required
secret
Marmot API key (generate from Settings > API Keys)

~/.cursor/mcp.json

{
  "mcpServers": {
    "marmot": {
      "url": "https://{marmot_host}/api/v1/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

Search assets — Find any data asset in seconds with full-text search, structured queries, boolean logic, and metadata filters
Explore lineage — Trace data flows from source to destination and analyze impact before making changes
Query metadata — Access rich metadata for any asset type (tables, topics, queues, APIs, dashboards) through MCP
Discover ownership — Identify data asset owners and team collaboration context

Use cases

Help AI agents understand your data landscape by querying real metadata instead of guessing
Trace data lineage to understand dependencies before making schema or pipeline changes
Discover which team owns a specific data asset and find relevant documentation
Search across all cataloged data assets (databases, message queues, APIs, dashboards) from a single interface
Enable AI tools to make informed decisions about data usage based on certified, up-to-date metadata

Marmot Data Catalog MCP server FAQ

What is the Marmot Data Catalog MCP server?

Marmot is an open-source data catalog that exposes certified metadata about your data assets to AI agents through MCP. It allows you to catalog tables, topics, queues, APIs, and dashboards, then makes that metadata accessible to both your team and AI tools for discovery and lineage exploration.

Is Marmot free?

Yes, Marmot is completely free and open-source under the MIT License. There are no licensing costs, and you can self-host it without any restrictions.

How do I deploy Marmot?

Marmot ships as a single binary with no complex infrastructure required. Follow the deployment guide at marmotdata.io/docs/Deploy, or try the live demo at demo.marmotdata.io to get started in minutes.

What data sources can I catalog?

Marmot supports cataloging tables (databases, data warehouses), topics (message queues, event streams), queues (job queues, messaging systems), APIs (REST, GraphQL, internal services), and dashboards (visualization tools, BI platforms) through its plugin system.

How does Marmot integrate with AI agents?

Marmot exposes certified context through MCP, allowing AI agents to query real metadata about your data assets. This enables AI tools to understand your data landscape, trace lineage, and make informed decisions based on actual metadata rather than guessing.

Where can I get help or contribute?

Join the Discord community at discord.gg/TWCk7hVFN4, check the documentation at marmotdata.io/docs, or report issues and contribute via GitHub. All types of contributions—bug reports, documentation improvements, and new plugins—are welcome.

README (reference)

Source of truth, from the repository.

Marmot

Discover any data asset in seconds. Then let your AI do the same.

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

Documentation • Live Demo • Deploy • Community

</div>

What is Marmot?

Marmot is an open-source data catalog for teams who want powerful data discovery without enterprise complexity. Catalog every data asset, enrich it with the context that matters and make it accessible to your team and your AI tools.

Unlike traditional catalogs that require extensive infrastructure and configuration, Marmot ships as a single binary with an intuitive UI, making it easy to deploy and start cataloging in minutes.

<div align="center"> <a href="https://www.youtube.com/watch?v=_JBcQGj_bFU"> <img src="https://img.youtube.com/vi/_JBcQGj_bFU/maxresdefault.jpg" alt="Watch the Marmot demo on YouTube" width="480"> </a> <p><a href="https://www.youtube.com/watch?v=_JBcQGj_bFU">▶ Watch the 2-minute demo</a></p> </div>

Features

Search everything: Find any data asset in seconds with full-text search plus structured queries, boolean logic and metadata filters.
Interactive lineage: Trace data flows from source to destination and analyse impact before making changes.
Metadata-first: Store rich metadata for any asset type, from tables and topics to APIs and dashboards.
Team collaboration: Assign ownership, document business context and maintain shared glossaries.
AI-ready: Expose certified context through MCP, the API and the UI.

Deploy

New to Marmot? Follow the Deploy documentation for a guided setup, or try the live demo.

Development

See Local Development for how to get started developing locally.

Community

Join our Discord community for help, feedback and updates on new features.

Contributing

All types of contributions are encouraged and valued!

Report bugs or suggest features via GitHub Issues
Improve documentation
Build new plugins for data sources

Before contributing, please check out the Contributing Guide.

FAQ

What is Marmot?

Marmot is an open-source data catalog for teams who want powerful data discovery without enterprise complexity. It catalogs every data asset (tables, topics, queues, APIs), enriches it with context, and makes it accessible to both your team and AI tools. Unlike traditional catalogs requiring extensive infrastructure, Marmot ships as a single binary with an intuitive UI.

Why Use Marmot?

Feature	Benefit
Search Everything	Find any data asset in seconds with full-text search, structured queries, boolean logic, and metadata filters
Interactive Lineage	Trace data flows from source to destination, analyze impact before making changes
Metadata-First	Store rich metadata for any asset type (tables, topics, APIs, dashboards)
Team Collaboration	Assign ownership, document business context, maintain shared glossaries
AI-Ready	Expose certified context through MCP, API, and UI
Single Binary	No complex infrastructure required, deploy in minutes

How Does Marmot Integrate with AI Agents?

Marmot exposes certified context through MCP (Model Context Protocol), enabling AI agents to query real metadata about your data assets. This allows AI tools to understand your data landscape, trace lineage, and make informed decisions based on actual metadata rather than guessing.

What Data Sources Can I Catalog?

Marmot supports cataloging various data asset types through its plugin system:

Tables (databases, data warehouses)
Topics (message queues, event streams)
Queues (job queues, messaging systems)
APIs (REST, GraphQL, internal services)
Dashboards (visualization tools, BI platforms)

How Do I Deploy Marmot?

Quick Start Options:

Method	Description
Documentation Guide	Follow the Deploy guide for step-by-step setup
Live Demo	Try the live demo before deploying
Single Binary	Download and run the single binary for your platform

Is Marmot Free?

Yes! Marmot is open-source software licensed under the MIT License. You can use, modify, and distribute it freely. Self-hosting is completely free with no licensing costs.

How Can I Contribute?

All contributions are welcome:

Report bugs or suggest features via GitHub Issues
Improve documentation (README, guides, API docs)
Build new plugins for additional data sources
Check the Contributing Guide before contributing

Where Can I Get Help?

Resource	Link
Documentation	marmotdata.io/docs
Discord Community	Join Discord
GitHub Issues	Report issues
Live Demo	Try demo

License

Marmot is open-source software licensed under the MIT License.

Related MCP servers

io.github.maroondlabs/sourcebook

Maintained

Live codebase intelligence for AI agents: conventions, blast radius, import graphs, git insights.

HTML

View repository →

io.github.marras0914/agent-toolbelt-mcp

Active

19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.

TypeScript

View repository →

Cordon for MCP

Active

Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.

TypeScript

MIT

View repository →

Refactoring MCP Server

Stale

MCP server exposing Martin Fowler's refactoring catalog to LLMs with 71+ refactorings

Python

MIT

View repository →

Business Entity

Maintained

SEC company search and SBA business resources. 4 MCP tools for business intelligence.

TypeScript

MIT

View repository →

Competitive Intel

Maintained

SEC filings, patent data, and trade data. 4 competitive intel tools.

TypeScript

MIT

View repository →