fireproof-storage/mcp-database-server
by Various
Store and load JSON documents from LLM tool use
MCP
fireproof-storage/mcp-database-server
Added 1 June 2026
Overview
Implements a Model Context Protocol (MCP) server for reading and writing JSON documents. Designed to let LLM tool-use sessions store and load structured data from a persistent database.
Best for
Best for
Developers building MCP-based tools or agents that need straightforward, file-backed JSON persistence
Use cases
- Save and retrieve conversation context or session state in MCP-compatible AI assistants
- Persist outputs from tool calls for later analysis or reuse
- Enable agents to share JSON-based data across multiple tool invocations
How to use
Tools exposed
npm
Tested with
Claude Desktop
Example client config
{\n "mcpServers": {\n "fireproof": {\n "command": "/path/to/fireproof-mcp/build/index.js"\n }\n }\n} Notes
Implements a Model Context Protocol (MCP) server for reading and writing JSON documents. Designed to let LLM tool-use sessions store and load structured data from a persistent database.
32 stars on GitHub. Last updated 2024-12-19.
Use cases
- Save and retrieve conversation context or session state in MCP-compatible AI assistants
- Persist outputs from tool calls for later analysis or reuse
- Enable agents to share JSON-based data across multiple tool invocations
Pros
- Lightweight JavaScript implementation with minimal dependencies
- Simple JSON document storage, easy to inspect and debug
- Works within the MCP ecosystem, allowing direct integration with supported LLM tools
Cons
- Limited to JSON document storage, not a general-purpose SQL or NoSQL database
- Low community adoption (32 stars) may mean fewer examples or slower evolution
- No built-in authentication or access control—designed for local or trusted environments
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Lightweight JavaScript implementation with minimal dependencies
- Simple JSON document storage, easy to inspect and debug
- Works within the MCP ecosystem, allowing direct integration with supported LLM tools
Cons
- Limited to JSON document storage, not a general-purpose SQL or NoSQL database
- Low community adoption (32 stars) may mean fewer examples or slower evolution
- No built-in authentication or access control—designed for local or trusted environments
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.