# HutchDB

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

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 22
- Author: ExpeditedProjects
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ExpeditedProjects/hutchdb
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/hutchdb

## What it 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.

## Requirements
- Needs: Docker
- Remote server: `https://app.hutchdb.com/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http hutchdb https://app.hutchdb.com/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add hutchdb --url https://app.hutchdb.com/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "hutchdb": {
            "url": "https://app.hutchdb.com/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "hutchdb": {
            "type": "http",
            "url": "https://app.hutchdb.com/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http hutchdb https://app.hutchdb.com/api/mcp
```

## When to use it
- 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
- 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`.

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27669
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49845

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md