What databases does Isthmus support?
Isthmus works exclusively with PostgreSQL databases.

@guillermoBallester
Basic information
A single binary MCP server that gives Claude, Cursor, and any MCP client safe, read-only access to your PostgreSQL database. Runs locally over stdio or HTTP — your credentials never leave your machine.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"isthmus": {
"command": "isthmus",
"env": {
"DATABASE_URL": "postgres://user:pass@localhost:5432/mydb"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Isthmus is a local MCP server that gives AI models safe, read-only access to your PostgreSQL database. It runs as a single binary on your machine; credentials never leave.
Install Isthmus via the install script or Docker, set the DATABASE_URL environment variable, and add it to your MCP client configuration (e.g., Claude Desktop JSON). Then ask your AI questions about your database.
Isthmus works exclusively with PostgreSQL databases.
Yes. Isthmus only allows `SELECT` and `EXPLAIN` statements, enforced via AST-level validation using PostgreSQL’s own parser.
Column masking allows per-column redact, hash, partial, or null masking, enforced server-side before results are returned.
Isthmus supports stdio (for desktop MCP clients) and HTTP (for web-based clients and remote access).
Isthmus works with any MCP client, including Claude Desktop, Cursor, Windsurf, Gemini CLI, VS Code, and ChatGPT Desktop.
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
The official Redis MCP Server is a natural language interface designed for agentic applications to manage and search data in Redis efficiently
Comments