Jazz MCP Server
Enables AI assistants to create, read, update, and delete data in local-first apps built with the Jazz framework, with support for sync, auth, and rich data types.
README
Jazz MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with local-first apps built with the Jazz framework.
What is this?
The Jazz MCP Server allows AI assistants like Claude, ChatGPT, and others to:
- Create, read, update, and delete data in Jazz applications
- Sync data between devices using Jazz's distributed state capabilities
- Manage authentication and user profiles
- Work with rich text, media, and other data types supported by Jazz
Prerequisites
- Node.js 22.x or higher
- npm or pnpm
- A Jazz application to connect to (or create one with
npx create-jazz-app@latest)
Installation
-
Clone this repository:
git clone https://github.com/bensleveritt/jazz-mcp-server.git cd jazz-mcp-server -
Install dependencies:
npm install # or with pnpm pnpm install -
Copy the environment example file and configure it for your needs:
cp .env.example .env -
Build the server:
npm run build # or with pnpm pnpm build
Usage
Start the MCP server:
npm start
# or with pnpm
pnpm start
For development with auto-restart:
npm run dev
# or with pnpm
pnpm dev
Connecting AI Assistants
The server exposes an MCP-compatible API at http://localhost:3000 (or your configured host/port).
In Cursor
- Open a project in Cursor
- Click on the Cursor AI settings
- Add a custom MCP server with the URL
http://localhost:3000 - Use the API key configured in your
.envfile (if auth is enabled)
In Other AI Assistants
Follow the relevant documentation for your AI assistant to connect to an MCP server at the URL http://localhost:3000.
Available Tools
This MCP server provides the following tools for AI assistants:
jazz.listApps- List available Jazz applicationsjazz.getAppData- Get data from a Jazz applicationjazz.updateAppData- Update data in a Jazz applicationjazz.createAppData- Create new data in a Jazz applicationjazz.deleteAppData- Delete data from a Jazz applicationjazz.auth.createUser- Create a new userjazz.auth.login- Log in an existing user
Development
The server is built with TypeScript and uses the official MCP protocol implementation.
Key files:
src/index.ts- Main entry pointsrc/config.ts- Configuration loadingsrc/server.ts- MCP server implementationsrc/tools/- Individual tool implementationssrc/jazz/- Jazz integration
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.