Skip to main content
MCP server CX Codex

HutchDB — Claude Code MCP server: what it does, how to install

A schemaless structured database for AI agents. It gives multiple assistants a shared storage space to query and update records across chats.

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http hutchdb https://app.hutchdb.com/api/mcp
Open on GitHub

What HutchDB does

Instead of dumping context into ephemeral markdown notes, HutchDB supplies an MCP-accessible database layer. Assistants store raw JSON records into collections that build themselves on the initial write. The engine stores everything inside Postgres JSONB, unlocking text search along with MongoDB-style filter operators.

The core engine runs headless without dashboards or web logins. You spin it up via Docker on port 3000 or directly with Node.js against a HUTCH_DATABASE_URL. Outside of local tests, running the server without setting HUTCH_API_KEY leaves every endpoint unauthenticated.

What it helps with

  • persist research and competitor notes across separate chat sessions
  • pass structured records between different AI agents in a pipeline
  • track bugs and task backlogs without predefining database tables
  • query stored documents using JSONB containment and comparison filters

Example prompts for the agent

  • Save these bug reports into the bug-reports collection with severity high.
  • Query customer-interviews for any records mentioning checkout issues.
  • Fetch all entries in leads marked with status new.

How to install HutchDB

Platform CLI: remote server

claude mcp add --transport http hutchdb https://app.hutchdb.com/api/mcp

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about HutchDB

How to install HutchDB in Claude Code?

Run claude mcp add --transport http hutchdb https://app.hutchdb.com/api/mcp in your terminal.

What does HutchDB do?

It acts as a shared document database for AI agents via the Model Context Protocol. Connected clients can save arbitrary JSON records, inspect previous session data, and run structured queries.

Does HutchDB require predefined database schemas?

No upfront schema design is needed because collections automatically generate upon the first record write. It relies on Postgres JSONB to hold flexible record formats.

Similar MCP servers

All MCP servers for Data and databases →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor