$ loading_
Connect to PostgreSQL via MCP for queries, schema inspection, and database changes.
This MCP tool is აღწcribed as interacting with PostgreSQL databases, including queries, DDL/DML, and schema inspection, which implies access to database data and the ability to modify schema or records. The materials are sparse, but there is no stated exfiltration to unrelated remote endpoints or extra secret requirements; overall it is mainly a caution-level database tool, with added supply-chain concern due to weak provenance signals.
The materials explicitly state 'required secrets/environment variables: none', and no API key, token, or third-party account credential is requested. Still, note that real PostgreSQL connections commonly involve database credentials, though this is not declared in the provided materials.
By design, the tool interacts with PostgreSQL databases, so queries and possibly user-provided data will be sent to the target database. No fixed remote endpoint is declared, and there is no evidence of exfiltration to unrelated services; however, database interaction inherently involves network connectivity or at least inter-process communication, so the actual destination should be verified.
System checks indicate that this tool executes code/spawns processes, which is a common MCP capability. The materials do not show requests for system privileges beyond what database interaction would normally require, and no obviously suspicious execution chain is described, but it should still be run with least privilege.
It claims support for queries, DDL, DML, and schema inspection, meaning it can not only read database contents but also potentially modify schema and data; the effective scope depends on the connected database account's privileges. No local file read/write scope is described, and no obvious overbroad authorization is stated, but its database-level mutation capability warrants caution.
A positive factor is that there is an open-source repository available for review; however, the source is a third-party registry, the README is absent, the license is undeclared, community adoption is 0 stars, and maintenance status is unknown, which weakens transparency and maturity. It is better suited to source and dependency review before use in sensitive environments.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "pgsql-mcp-server" yet — see the docs or source repo.
Connect to the PostgreSQL database and query daily order counts and revenue from the orders table for the last 30 days, sorted by date ascending.
A reusable SQL query result showing date, order count, and revenue.
Inspect the users, orders, and payments tables in the current database, including columns, types, primary keys, and indexes, then summarize their relationships.
Detailed schema information and a summary of relationships between the tables.
In PostgreSQL, add a last_login_at timestamp column to the customers table and create a unique index on email; show the DDL before executing it.
The tool shows the DDL first, then applies the changes and returns the result or any errors.
Query PostgreSQL, inspect tables, and explore schemas through MCP clients.
Safely query and inspect PostgreSQL databases without enabling risky write operations by default.
Connect AI assistants to PostgreSQL for secure querying, management, and analysis.
Safely explore PostgreSQL schemas and run controlled read or write queries.
Safely inspect and query PostgreSQL databases using natural language.
Access PostgreSQL in read-only mode for queries, tables, and schema inspection.