What is the difference between the query and uploadCsv tools?
`query` executes read-only SQL queries within a READ ONLY transaction; `uploadCsv` executes read and write queries within a READ AND WRITE transaction.
@Pratye
Basic information
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.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"postgres": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"mcp/postgres",
"postgresql://host.docker.internal:5432/mydb"
]
}
}
}Execute read-only SQL queries against the connected database
Upload and process a CSV file into database tables
MEC Postgres is a Model Context Protocol (MCP) server that provides read and write access to PostgreSQL databases. It enables LLMs to inspect database schemas and execute SQL queries.
Use with Claude Desktop by adding the server configuration to the mcpServers section of claude_desktop_config.json. The server runs via Docker and connects to a PostgreSQL database using a connection URL (e.g., postgresql://user:password@host:port/db-name). Replace the database name and credentials as needed.
`query` executes read-only SQL queries within a READ ONLY transaction; `uploadCsv` executes read and write queries within a READ AND WRITE transaction.
Use a PostgreSQL connection URL (e.g., `postgresql://user:password@host:port/db-name`) when running the Docker container.
Yes, username and password can be included in the PostgreSQL connection URL.
The server is distributed as a Docker image; Docker is required to run it.
Local MCP server for DuckDB and MotherDuck
A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases
A Model Context Protocol (MCP) server implementation that provides database capabilities for Chroma
Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.
Connect ClickHouse to your AI assistants.
Comments