pg-mcp-server

stuzero/pg-mcp-server

4.4

pg-mcp-server is hosted online, so all tools can be tested directly either in theInspector tabor in theOnline Client.

If you are the rightful owner of pg-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

unknown

Try pg-mcp-server with chat:

MCPHub score:4.36

Has a README

Github repo has a README.md.

Has a License

Github repo has license info.

Server can be inspected

View server inspector

Server schema can be extracted

Can get at lease one tool info from the README or server.

Online hosted on MCPHub

Can be automatically deployed by MCPHub.

Has social accounts

Do not have any social accounts.

Claimed by the author or certified by MCPHub

If you are the author, claim authorship

AI Evaluation Report
Total Score: 4/10

The agent demonstrates a clear understanding of its capabilities related to PostgreSQL database operations, including connecting to a database, executing read-only queries, and analyzing execution plans. However, the tests reveal a consistent issue with the agent's inability to perform tasks due to missing input, specifically the PostgreSQL connection string. This indicates a limitation in handling incomplete inputs or providing guidance on what is needed to proceed. Additionally, there was a tool malfunction in one instance, suggesting potential reliability issues. Overall, the agent's performance is hindered by its dependency on external inputs and occasional technical errors.

  • Test case 1
    Score: 6/10
    Perform the operation of connecting to a PostgreSQL database, executing the query `SELECT * FROM users WHERE age > 30;`, and analyzing its execution plan in JSON format.

    No valid answer is generated due to invalid input. The response indicates that a PostgreSQL connection string is required to proceed with the task, but it was not provided in the input. Therefore, the task cannot be completed without this necessary information.

  • Test case 2
    Score: 6/10
    Perform the operation of connecting to a PostgreSQL database, executing the query `SELECT * FROM orders WHERE order_date >= '2025-01-01';`, and analyzing its execution plan in JSON format.

    No valid answer is generated due to invalid input. The response indicates that the task requires a PostgreSQL connection string to proceed, which was not provided in the input. Without this connection string, the tool cannot connect to the database to execute the query and analyze its execution plan.

  • Test case 3
    Score: 2/10
    Perform the operation of connecting to a PostgreSQL database, executing the query `SELECT * FROM customers WHERE city = 'New York';`, and analyzing its execution plan in JSON format.

    No valid answer is generated due to tool malfunction. The response indicates that there was an error executing the query and the explain command, with the message: 'Error executing tool pg_query: [Errno -2] Name or service not known'. This suggests a possible issue with the database connection or configuration, leading to the failure of the tool to perform the task.

  • Test case 4
    Score: 6/10
    Perform the operation of connecting to a PostgreSQL database, executing the query `SELECT * FROM employees WHERE department = 'Sales';`, and analyzing its execution plan in JSON format.

    No valid answer is generated due to invalid input. The response does not provide the PostgreSQL connection string needed to connect to the database and execute the query. Without this information, the task cannot be completed.

  • Test case 5
    Score: 6/10
    Perform the operation of connecting to a PostgreSQL database, executing the query `SELECT * FROM products WHERE price > 100;`, and analyzing its execution plan in JSON format.

    No valid answer is generated due to invalid input. The response indicates that the task requires a PostgreSQL connection string to proceed, which was not provided in the input. Without this connection string, the tool cannot connect to the database to execute the query and analyze its execution plan.