mcp-postgres-server
MCP server providing PostgreSQL and Vertica database access with tools for querying, listing tables, and testing connections.
README
PostgreSQL & Vertica MCP Server
A professional Model Context Protocol (MCP) server providing## π§© Project Structure
mcp-postgres-server/
βββ postgres_main.py # PostgreSQL server entry point
βββ vertica_main.py # Vertica server entry point
βββ config.py # Configuration and logging
βββ servers/
β βββ postgres_server.py # PostgreSQL MCP server implementation
β βββ vertica_server.py # Vertica MCP server implementation
βββ run_postgres_mcp.sh / run_postgres_mcp.bat # PostgreSQL wrapper scripts
βββ run_vertica_mcp.sh / run_vertica_mcp.bat # Vertica wrapper scripts
βββ setup_mcp.sh # Setup and testing script
βββ test_connection.py # PostgreSQL connection test
βββ test_vertica_connection.py # Vertica connection test
βββ client_json_config_example/ # Editor config templates for both servers
βββ .env.example # Environment template
βββ README.md # This file
```se access from AI tools like Claude Desktop and Zed Editor.
**Supports:** PostgreSQL and Vertica databases
---
## π Features
- **Dual Database Support:** PostgreSQL and Vertica database access
- **Direct Database Access:** Securely run SQL queries from AI assistants
- **Easy Integration:** Works out-of-the-box with Claude Desktop and Zed Editor
- **Cross-Platform:** Supports Linux, macOS, and Windows
- **Automatic Lifecycle:** Server starts/stops automatically with your editor
- **Safe & Audited:** Parameterized queries, error handling, and logging
---
## β‘ Quick Start
### 1. Prerequisites
- Python 3.13+
- PostgreSQL or Vertica database (or both)
- [`uv`](https://docs.astral.sh/uv/) package manager
### 2. Installation
```bash
git clone https://github.com/Nayab-zak/mcp-postgres-server.git
cd mcp-postgres-server
uv sync
cp .env.example .env # Edit .env with your DB details
3. Configuration
Edit .env with your database connection strings:
For PostgreSQL:
DB_URL=postgresql://username:password@localhost:5432/database_name
For Vertica:
VERTICA_HOST=localhost
VERTICA_PORT=5433
VERTICA_DB=VMart
VERTICA_USER=dbadmin
VERTICA_PASSWORD=your_password
For Claude Desktop/Zed Editor, see client_json_config_example/ for ready-to-use config templates:
claude_desktop_config.json- PostgreSQL onlyvertica_claude_desktop_config.json- Vertica onlycombined_claude_desktop_config.json- Both serverszed_settings.json- PostgreSQL only for Zedvertica_zed_settings.json- Vertica only for Zedcombined_zed_settings.json- Both servers for Zed
4. Run the Servers
PostgreSQL Server:
- Linux/macOS:
./run_postgres_mcp.sh - Windows:
run_postgres_mcp.bat
Vertica Server:
- Linux/macOS:
./run_vertica_mcp.sh - Windows:
run_vertica_mcp.bat
Or let Claude Desktop/Zed Editor start the servers automatically when you ask database questions.
π₯οΈ How to Check if Servers are Running
PostgreSQL Server:
- Linux/macOS:
ps aux | grep PostgresMCPServer # or ps aux | grep "python postgres_main.py" - Windows:
tasklist | findstr PostgresMCPServer tasklist | findstr python
Vertica Server:
- Linux/macOS:
ps aux | grep VerticaMCPServer # or ps aux | grep "python vertica_main.py" - Windows:
tasklist | findstr VerticaMCPServer tasklist | findstr python
If you only see the grep/findstr line, the server is not running.
π Server Lifecycle
- Automatic: Servers start/stop automatically with Claude Desktop or Zed Editor.
- Manual: You can start/stop them from the terminal for testing.
- No need to restart manually during normal useβthe editor manages them for you.
- Multiple servers: You can run both PostgreSQL and Vertica servers simultaneously.
π οΈ Available Tools
| Tool | Description | Example Usage |
|---|---|---|
test_connection |
Test DB connectivity | "Test the database connection" |
query |
Execute SQL queries | "Show me the first 5 users" |
list_tables |
List all tables with metadata | "List all tables in the database" |
π§βπ» Manual Testing
PostgreSQL:
uv run python test_connection.py # Test PostgreSQL connection
uv run python postgres_main.py # Run PostgreSQL server directly
Vertica:
uv run python test_vertica_connection.py # Test Vertica connection
uv run python vertica_main.py # Run Vertica server directly
π§© Project Structure
mcp-postgres-server/
βββ main.py # Entry point
βββ config.py # Configuration and logging
βββ servers/
β βββ postgres_server.py # MCP server implementation
βββ run_mcp.sh / run_mcp.bat # Wrapper scripts
βββ setup_mcp.sh # Setup and testing script
βββ test_connection.py # DB connection test
βββ client_json_config_example/ # Editor config templates
βββ .env.example # Environment template
βββ README.md # This file
π Troubleshooting
Connection failed?
- PostgreSQL: Check if PostgreSQL is running:
pg_isready -h localhost -p 5432 - Vertica: Check if Vertica is running and accessible on the configured port
- Verify credentials in
.env
Server won't start?
- PostgreSQL: Test connection:
uv run python test_connection.py - Vertica: Test connection:
uv run python test_vertica_connection.py - Check logs:
tail -f logs/app.log
Editor integration issues?
- Linux/macOS: Ensure full path to wrapper scripts in editor config and make them executable
- Windows: Ensure full path to
.batscripts in editor config with proper backslashes - Use the appropriate config templates in
client_json_config_example/ - Restart your editor after config changes
π Security Notes
- Parameterized queries prevent SQL injection
- All DB operations are logged
- Supports read-only DB users for safety
- Error messages are sanitized
π License
MIT License β see the LICENSE file for details.
π€ Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/your-feature) - Commit your changes (
git commit -m 'Add your feature') - Push to the branch (
git push origin feature/your-feature) - Open a Pull Request
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.
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.
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.
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.