Marmot Data Catalog
Give your coding agent searchable access to tables, pipelines, lineage, and owners in your Marmot data catalog instance.
Overview
Marmot Data Catalog is an MCP server for the Operate phase that lets agents search your Marmot instance, explore asset lineage, and surface ownership via authenticated remote HTTP tools.
What is this MCP server?
- Remote streamable-http MCP endpoint against your self-hosted Marmot hostname
- Search catalog assets and explore lineage from the agent thread
- Resolve ownership and metadata without leaving Claude Code or Cursor
- Requires Marmot API key from Settings and your instance host URL
- Open-source Marmot repo on GitHub (server schema version 1.0.0)
- MCP server schema version 1.0.0
- Single remote endpoint pattern: /api/v1/mcp on your Marmot host
- Required secret header: X-API-Key
What problem does it solve?
Agents refactor data code blind because table names, lineage, and owners live in a separate catalog UI nobody opens during a sprint.
Who is it for?
Indie builders or tiny data teams already running Marmot who want catalog search and lineage inside Claude Code, Cursor, or Codex.
Skip if: Greenfield projects with no catalog yet, or teams that only need local file search without a Marmot deployment.
What do I get? / Deliverables
After you register Marmot MCP with host and API key, the agent can query live catalog metadata while you edit pipelines or debug production data issues.
- Agent-callable catalog search and lineage queries against your Marmot host
- Ownership and asset metadata surfaced in the coding session
Recommended MCP Servers
Journey fit
Data catalogs matter most once you are running real pipelines and need to know what exists, who owns it, and what breaks downstream. Infra and data-platform shelf fits catalog search and lineage when operating production data assets, not when sketching an MVP schema.
How it compares
MCP integration to a data catalog, not an in-repo codebase intelligence skill like Sourcebook.
Common Questions / FAQ
Who is Marmot Data Catalog MCP for?
Solo builders and small teams who self-host Marmot and want agents to discover datasets, lineage, and owners without switching to the web UI.
When should I use Marmot Data Catalog MCP?
Use it during operate and iterate work when you need accurate asset search, downstream lineage, or owner lookup before changing pipelines or schemas.
How do I add Marmot Data Catalog MCP to my agent?
Add the remote MCP server URL https://{marmot_host}/api/v1/mcp, set the marmot_host variable to your instance, and supply X-API-Key from Marmot Settings > API Keys.