mirror of https://github.com/encounter/adk-python.git synced 2026-03-30 10:57:20 -07:00

Files

T

Vrajesh Babu A V 45a2168e0e chore: Adds a new sample agent that demonstrates how to integrate PostgreSQL databases using the Model Context Protocol (MCP)

## What's Added

- **PostgreSQL MCP Agent** ([mcp_postgres_agent/agent.py](cci:7://file:///Users/admin/git%20repos/adk-python/contributing/samples/mcp_postgres_agent/agent.py:0:0-0:0)): A fully functional agent that connects to PostgreSQL databases via the `postgres-mcp` MCP server
- **Comprehensive README** ([mcp_postgres_agent/README.md](cci:7://file:///Users/admin/git%20repos/adk-python/contributing/samples/mcp_postgres_agent/README.md:0:0-0:0)): Documentation with setup instructions, configuration details, and example queries
- **Environment Configuration**: Support for secure credential management via `.env` files

## Key Features

- **MCP Integration**: Demonstrates proper use of `MCPToolset` with `StdioConnectionParams`
- **Zero Installation**: Uses `uvx` to run the MCP server without manual installation
- **Secure Credentials**: Database connection strings passed via environment variables
- **Production-Ready**: Uses Gemini 2.0 Flash with unrestricted access mode for full database operations

## Technical Details

- **Model**: Gemini 2.0 Flash
- **MCP Server**: `postgres-mcp` (via `uvx`)
- **Connection**: StdioConnectionParams with 60-second timeout
- **Environment Variable**: Maps `POSTGRES_CONNECTION_STRING` to `DATABASE_URI`

## Testing

The agent has been tested with:
- PostgreSQL database connections (local and remote)
- Schema inspection queries
- Data querying operations
- Table listing and management

## Example Queries

Users can interact with the agent using natural language queries like:
- "What tables are in the database?"
- "Show me the schema for the users table"
- "Query the first 10 rows from the products table"

This sample serves as a reference implementation for developers looking to integrate PostgreSQL databases with ADK agents using MCP.

COPYBARA_INTEGRATE_REVIEW=https://github.com/google/adk-python/pull/3182 from Vrajesh-Babu:postgres-mcp f3b3846abae37ae376d3554624ac2b1be82f7adc
PiperOrigin-RevId: 822865931

2025-10-22 21:44:25 -07:00

__init__.py

chore: Adds a new sample agent that demonstrates how to integrate PostgreSQL databases using the Model Context Protocol (MCP)

2025-10-22 21:44:25 -07:00

agent.py

chore: Adds a new sample agent that demonstrates how to integrate PostgreSQL databases using the Model Context Protocol (MCP)

2025-10-22 21:44:25 -07:00

README.md

chore: Adds a new sample agent that demonstrates how to integrate PostgreSQL databases using the Model Context Protocol (MCP)

2025-10-22 21:44:25 -07:00

README.md

PostgreSQL MCP Agent

This agent uses the PostgreSQL MCP server to interact with PostgreSQL databases. It demonstrates how to:

Connect to a PostgreSQL database using MCP (Model Context Protocol)
Use uvx to run the MCP server without manual installation
Pass database credentials securely via environment variables

Prerequisites

PostgreSQL Database: You need access to a PostgreSQL database with a connection string
uvx: The agent uses uvx (part of the uv package manager) to run the MCP server

Setup Instructions

1. Configure Database Connection

Create a .env file in the mcp_postgres_agent directory:

POSTGRES_CONNECTION_STRING=postgresql://user:password@host:port/database

Example connection string format:

postgresql://username:password@localhost:5432/mydb
postgresql://postgres.xyz:password@aws-region.pooler.supabase.com:5432/postgres

2. Run the Agent

Start the ADK Web UI from the samples directory:

adk web

The agent will automatically:

Load the connection string from the .env file
Use uvx to run the postgres-mcp server with unrestricted access mode
Connect to your PostgreSQL database

3. Example Queries

Once the agent is running, try these queries:

"What tables are in the database?"
"Show me the schema for the users table"
"Query the first 10 rows from the products table"
"What indexes exist on the orders table?"
"Create a new table called test_table with columns id and name"

Configuration Details

The agent uses:

Model: Gemini 2.0 Flash
MCP Server: postgres-mcp (via uvx)
Access Mode: Unrestricted (allows read/write operations). Warning: Using unrestricted mode in a production environment can pose significant security risks. It is recommended to use a more restrictive access mode or configure database user permissions appropriately for production use.
Connection: StdioConnectionParams with 60-second timeout
Environment Variable: DATABASE_URI (mapped from POSTGRES_CONNECTION_STRING)

Troubleshooting

Ensure your POSTGRES_CONNECTION_STRING is correctly formatted
Verify database credentials and network access
Check that uv is installed (pip install uv or brew install uv)