mcpField
P
PostgreSQL Products MCP Server

PostgreSQL Products MCP Server

Local
github.com/michael7736Databases1Updated 82w ago

About PostgreSQL Products MCP Server

PostgreSQL Products MCP Server lets MCP clients query a PostgreSQL database containing product information. Its `run_sql_query` tool accepts read-only SELECT statements.

Key features

  1. 01Run read-only SQL SELECT queries
  2. 02Connect to a configured PostgreSQL database
  3. 03Query product information

Use cases

  1. 01Retrieve product details from PostgreSQL
  2. 02Check product stock or category data
  3. 03Run read-only product database queries from an MCP client

MCP support

Exposes the `run_sql_query` tool to MCP clients for read-only SELECT queries against the configured products database.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

PostgreSQL Products MCP Server

This is a Model Context Protocol (MCP) server designed to interact with a PostgreSQL database containing product information. It allows clients (like AI assistants) to query the database using SQL.

Prerequisites

  • Node.js (v18 or later recommended)
  • npm or yarn
  • Access to a PostgreSQL database with the products schema.

Installation

  1. Clone this repository (or download the source code):
    git clone https://github.com/michael7736/postgres-mcp-server.git
    cd postgres-mcp-server
    
  2. Install dependencies:
    npm install
    # or
    yarn install
    

Building

Compile the TypeScript code to JavaScript:

npm run build
# or
yarn build

This will create the executable file in the build/ directory (build/index.js).

Configuration

This server requires PostgreSQL connection details to be provided via environment variables when it's configured in your MCP client settings (e.g., cline_mcp_settings.json or claude_desktop_config.json).

The required environment variables are:

  • PGHOST: Hostname of the PostgreSQL server.
  • PGPORT: Port number of the PostgreSQL server (default: 5432).
  • PGUSER: Username for the database connection.
  • PGPASSWORD: Password for the database connection.
  • PGDATABASE: Name of the database to connect to.

Example MCP Settings Configuration:

{
  "mcpServers": {
    "postgres-products": {
      "command": "node",
      "args": ["/path/to/your/postgres-mcp-server/build/index.js"],
      "env": {
        "PGHOST": "your_db_host",
        "PGPORT": "5432",
        "PGUSER": "your_db_user",
        "PGPASSWORD": "your_db_password",
        "PGDATABASE": "your_db_name"
      },
      "disabled": false, // Ensure it's enabled
      "autoApprove": [] // Configure auto-approval if needed
    }
    // ... other servers
  }
}

Replace /path/to/your/postgres-mcp-server/build/index.js with the actual path to the built server file on your system, and fill in your specific database credentials in the env section.

Usage

Once configured and running via your MCP client, this server provides the following tool:

run_sql_query

Executes a read-only SQL query (SELECT statements only) against the configured products database.

Input Schema:

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "The SQL SELECT query to execute."
    }
  },
  "required": ["query"]
}

Example Tool Call:

<use_mcp_tool>
  <server_name>postgres-products</server_name>
  <tool_name>run_sql_query</tool_name>
  <arguments>
  {
    "query": "SELECT product_name, stock_quantity FROM products WHERE category = 'Electronics';"
  }
  </arguments>
</use_mcp_tool>

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.