Firebase Emulator MCP Server
Exposes Firebase emulator data (Firestore, Auth, Realtime Database, and logs) to AI coding assistants for local development inspection.
README
Firebase Emulator MCP Server
A Model Context Protocol server that exposes Firebase emulator data — Firestore, Auth, Logs, and Realtime Database — to AI agents over stdio.
Designed for local development workflows where AI coding assistants (Claude Code, GitHub Copilot, etc.) need to inspect emulator state without leaving the editor.
Created by Laish Glenberg, please drop a star on the repo if this package helped you!
Features
| Tool | Description |
|---|---|
emulator_status |
Ping all emulators and report reachability |
firestore_list_collections |
List root-level collection IDs |
firestore_query |
Query documents with optional field filters (==, >=, <=, in, etc.) |
firestore_get |
Fetch a single document by path (e.g. Member/abc123) |
rtdb_get |
Read any path from the Realtime Database emulator |
auth_list_users |
List Firebase Auth users |
auth_get_user |
Look up a user by email or localId |
emulator_logs |
Stream recent log entries from the emulator hub WebSocket |
Prerequisites
-
Node.js 18+ (native
fetchandWebSocket— v21+ recommended) -
Firebase emulators running locally — start from your project root:
firebase emulators:startThe server connects to the default emulator ports:
- Firestore:
8080 - Auth:
9099 - Realtime Database:
9000 - Hub (logs):
4500
- Firestore:
Install & Run
Via npm (recommended)
npm install -g firebase-emulator-mcp
firebase-emulator-mcp
VS Code / MCP Client Setup
Add to your project's .vscode/mcp.json or VS Code user settings:
{
"servers": {
"firebase-emulator": {
"type": "stdio",
"command": "node",
"args": ["./mcp-server/lib/index.js"],
"env": {
"FIREBASE_PROJECT_ID": "<proj_id>",
"FIREBASE_RTDB_NAMESPACE": "<proj_id>-default-rtdb"
}
}
}
}
Or if installed globally:
{
"servers": {
"firebase-emulator": {
"type": "stdio",
"command": "firebase-emulator-mcp",
"env": {
"FIREBASE_PROJECT_ID": "<proj_id>",
"FIREBASE_RTDB_NAMESPACE": "<proj_id>-default-rtdb"
}
}
}
}
Optionally can skip install and run directly through npx
{
"servers": {
"firebase-emulator": {
"type": "stdio",
"command": "npx",
"args": ["@lglen/firebase-emulator-mcp"],
"env": {
"FIREBASE_PROJECT_ID": "<proj_id>",
"FIREBASE_RTDB_NAMESPACE": "<proj_id>-default-rtdb"
}
}
}
}
For Claude Code or other MCP clients, use the same stdio configuration.
Project structure
mcp-server/
├── src/
│ └── index.ts # TypeScript source (all tools)
├── lib/ # Compiled output (git-ignored)
├── test.mjs # Smoke test runner
├── tsconfig.json
├── package.json
├── .gitignore
├── LICENSE # MIT
└── README.md
Configuration
Default emulator ports are defined in src/index.ts under the EMULATORS constant.
Edit them to match your firebase.json if you use non-standard ports:
| Service | Default Port |
|---|---|
| Firestore | 8080 |
| Auth | 9099 |
| Realtime DB | 9000 |
| Storage | 9199 |
| Emulator UI | 4000 |
| Hub (logs) | 4500 |
License
MIT
Author
Check me out on GitHub
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.