Model Context Protocol and Fireproof Demo: JSON Document Server
LocalAbout Model Context Protocol and Fireproof Demo: JSON Document Server
The Fireproof demo is an MCP server that stores JSON documents in a Fireproof database. It is an example for developers who want to see how a database can be used inside an MCP server so that AI systems can read and write structured documents.
Key features
- 01CRUD operations on JSON documents
- 02Querying documents sorted by any field
- 03Storage backed by a Fireproof database
- 04Debugging with the MCP Inspector
Use cases
- 01Letting Claude Desktop store and load JSON documents
- 02Learning how to connect a database to an MCP server
- 03Testing document read and write flows through LLM tool use
MCP support
The project is an MCP server that provides JSON document create, read, update, delete and sorted query capabilities to MCP clients such as Claude Desktop.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEModel Context Protocol and Fireproof Demo: JSON Document Server
This is a simple example of how to use a Fireproof database in a Model Context Protocol server (used for plugging code and data into A.I. systems such as Claude Desktop).
This demo server implements a basic JSON document store with CRUD operations (Create, Read, Update, Delete) and the ability to query documents sorted by any field.
Installation
Install dependencies:
npm install
npm build
Running the Server
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"fireproof": {
"command": "/path/to/fireproof-mcp/build/index.js"
}
}
}
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.