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 |
|---|---|
| query-tableC | Query data from a specific table with filtering, pagination, and sorting. Supports WHERE conditions with exact matches, arrays (IN), and LIKE patterns. |
| get-schemaB | Get database schema information including tables, columns, data types, and optionally constraints. Useful for understanding database structure. |
| execute-queryC | Execute a parameterized SQL query with safety checks. Supports SELECT, INSERT, UPDATE, DELETE operations with parameter binding to prevent SQL injection. |
| insert-dataC | Insert new records into a table. Supports single or multiple records, conflict resolution (ignore/update), and returning inserted data. |
| update-dataB | Update existing records in a table. Requires WHERE conditions for safety. Supports complex WHERE clauses and returns updated records. |
| delete-dataA | Delete records from a table. Requires WHERE conditions for safety. Includes confirmation prompt for large deletions. |
| get-table-infoB | Get detailed information about a specific table including columns, constraints, indexes, and optionally statistics like row count and size. |
| connection-statusA | Check database connection status, view error details, and retry connection. Use retry: true to attempt reconnection when database is unavailable. |
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 8 tools
Most tools have distinct purposes, but there is some overlap between 'execute-query' and 'query-table' that could cause confusion. 'execute-query' handles general SQL operations, while 'query-table' is specifically for querying tables with filtering, but both can be used for SELECT queries, potentially leading to misselection. Other tools like 'insert-data', 'update-data', and 'delete-data' are clearly differentiated by their CRUD operations.
Tool names follow a consistent verb-noun pattern with hyphens throughout, such as 'execute-query', 'get-schema', and 'update-data'. All tools adhere to this naming convention, making them predictable and easy to understand. There are no deviations or mixed styles like camelCase or snake_case, ensuring high readability.
With 8 tools, the count is well-scoped for a PostgreSQL server, covering essential database operations like connection management, CRUD, schema inspection, and query execution. Each tool serves a clear purpose without redundancy, and the number is neither too thin nor overwhelming, fitting typical server needs in the 3-15 tool range.
The tool set provides comprehensive coverage for core PostgreSQL operations, including connection status, schema retrieval, CRUD operations, and query execution. Minor gaps exist, such as the lack of tools for managing database objects (e.g., creating/dropping tables or indexes) or handling transactions, but agents can work around these using 'execute-query' for most missing functions.