PostgreSQL MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| connect_databaseC | Connect to a PostgreSQL database |
| list_tablesB | List all tables in the current database |
| describe_tableB | Get detailed information about a table's structure, columns, and constraints |
| execute_queryA | Execute a read-only SQL query (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH statements only) |
| get_schemaB | Get an overview of the database schema including tables and their relationships |
| disconnect_databaseB | Disconnect from the current PostgreSQL database |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: connect/disconnect manage connections, list_tables enumerates tables, describe_table provides table details, get_schema shows relationships, and execute_query runs read-only SQL. An agent can easily distinguish between these functions.
All tools follow a consistent verb_noun pattern with snake_case naming (e.g., connect_database, describe_table, execute_query). The naming is predictable and readable throughout the set.
With 6 tools, the count is reasonable for a PostgreSQL server focused on schema exploration and read-only queries. It's slightly lean but covers core database interaction needs without bloat.
The tools cover connection management, schema inspection, and read-only queries well, but there are notable gaps: no write operations (INSERT, UPDATE, DELETE) or administrative functions (e.g., create/drop tables). This limits the server to read-only use cases, which may cause agent failures for broader database tasks.