About MEC Postgres
MEC Postgres is an MCP server for PostgreSQL that lets LLMs inspect table schemas and run queries. It separates read-only SQL querying from CSV upload processing, which can write data to database tables.
Key features
- 01Run read-only SQL queries
- 02Upload and process CSV files
- 03Load CSV data into database tables
- 04Provide table schema JSON resources
- 05Discover columns and types from database metadata
Use cases
- 01Inspect PostgreSQL table schemas
- 02Run read-only database queries
- 03Import CSV data into database tables
MCP support
The server exposes SQL query and CSV upload tools to MCP clients, along with schema resources containing column names and data types. Queries use read-only transactions, while CSV processing uses read-write transactions.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMEC PostgreSQL
A Model Context Protocol server that provides read and write access to PostgreSQL databases. This server enables LLMs to inspect database schemas and execute read and write queries.
Components
Tools
- query
- Execute read-only SQL queries against the connected database
- Input:
sql(string): The SQL query to execute - All queries are executed within a READ ONLY transaction
- uploadCsv
- Upload and process a CSV file into database tables
- Input:
sql(string): The SQL query to execute - All queries are executed within a READ AND WRITE transaction
Resources
The server provides schema information for each table in the database:
- Table Schemas (
postgres://<host>/<table>/schema)- JSON schema information for each table
- Includes column names and data types
- Automatically discovered from database metadata
Usage with Claude Desktop
To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your claude_desktop_config.json:
Docker
- when running docker on macos, use host.docker.internal if the server is running on the host network (eg localhost)
- username/password can be added to the postgresql url with
postgresql://user:password@host:port/db-name
{
"mcpServers": {
"postgres": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"mcp/postgres",
"postgresql://host.docker.internal:5432/mydb"]
}
}
}
Replace /mydb with your database name.
Building
Docker:
docker build -t mcp/postgres -f src/postgres/Dockerfile .
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Comments
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.