PostgreSQL
Runs read-only SQL against a Postgres database and returns the schema alongside results, which is what makes it usable without pasting table definitions into the prompt.
Archived upstream. This server still works, but it receives no fixes. Use it to understand an existing setup, not to start a new one.
What it does
Runs read-only SQL against a Postgres database and returns the schema alongside results, which is what makes it usable without pasting table definitions into the prompt. Point it at a replica or a read-only role; the server assumes you have already handled access control.
Install
npx -y @modelcontextprotocol/server-postgres postgresql://localhost/mydbClient configuration
Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.
{
"mcpServers": {
"postgres": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-postgres",
"postgresql://localhost/mydb"
]
}
}
}When to use it
Reach for this when the task needs database inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.
Other TypeScript servers
- Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
- Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
- Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude