What is the MCP Server?

The MCP (Model Context Protocol) Server is a Python server that acts as a bridge between Large Language Models (LLMs) and Firebase Firestore, enabling AI models to access and manipulate data within your Firestore database.

What is Firebase Firestore?

Firestore is a NoSQL document database built for automatic scaling, high performance, and ease of application development. It’s part of the Google Cloud Platform.

What is MCP (Model Context Protocol)?

MCP is an open protocol that standardizes how applications provide context to LLMs, allowing AI models to interact with external data sources and tools in a consistent manner.

What are the prerequisites for using the MCP Server?

You need Python 3.7+ (preferably 3.8+), Pip or uv, a Firebase project with Firestore enabled, and a Firebase service account key JSON file.

How do I install the MCP Server?

1. Clone/download the server files.
2. Set up your Firebase service account key.
3. Create a virtual environment (recommended).
4. Install the dependencies using pip install -r requirements.txt or uv pip install -r requirements.txt.

How do I run the MCP Server?

You can run the server directly using the run_server.sh script or by using the MCP CLI with the command mcp dev mcp_firebase_server.py.

What tools does the MCP Server expose?

The server exposes tools for querying Firestore collections, adding documents, listing collections, getting specific documents, listing subcollections, updating documents, and querying with filters.

How do I configure the MCP Server to connect to my Firebase project?

You need to set the SERVICE_ACCOUNT_KEY_PATH environment variable to the absolute path of your Firebase service account key JSON file. Optionally, you can set the FIREBASE_STORAGE_BUCKET environment variable if you plan to use Firebase Storage functionalities.

How does the MCP Server integrate with UBOS?

The MCP Server seamlessly integrates with the UBOS platform, allowing you to orchestrate AI agents, connect them with your enterprise data, build custom AI agents, and develop multi-agent systems.

What are some use cases for the MCP Server?

Use cases include intelligent product recommendations, automated inventory management, personalized treatment plans, fraud detection, personalized financial advice, and targeted marketing campaigns.

What security measures are in place to protect my data?

The MCP Server leverages Firebase authentication, secure service account key management, and data encryption to protect your data.

What is UBOS?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. Our platform helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.