postgres-mcp

execute_sql

Execute SQL against a chosen PostgreSQL database, with limits on rows returned to avoid excessive data.

Instructions

Execute SQL (max 50 rows returned)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "sql": "<sql>"
    },
    "name": "execute_sql"
  }
}

Input Schema

Name	Required	Description
`db`	No	Database id from list_databases
`sql`	Yes
`limit`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Aug 2, 2026

TDQS

C2.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses only the row limit ('max 50 rows returned') but does not mention possible mutations, side effects, permission requirements, or whether it can execute destructive SQL. This is a significant gap for a tool named execute_sql.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and front-loaded, with no wasted words. However, it is under-specified for a tool of this importance; the brevity is not a virtue given the missing safety and usage context. It earns a mid score for being concise but not appropriately sized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a powerful arbitrary SQL execution tool with no output schema and no annotations. The description utterly fails to provide safety context, distinguish from analysis siblings, or explain when to use it. Only the row limit is mentioned. The tool is severely incomplete for an agent to safely invoke.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 33%. The description adds no meaning for 'sql' or 'db' parameters. The row limit hint relates to 'limit' default but does not explain that it can be increased up to 500. Low coverage plus no parameter details in description means it does not compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

'Execute SQL' clearly states the verb and resource. It distinguishes from sibling tools (list_databases, explain_query, analyze_*) which are all read/analysis tools, while this is the only direct execution tool. However, it could be more specific about whether this is read-only or arbitrary DDL/DML.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use execute_sql vs alternatives like explain_query or list_databases. Does not mention exclusions (e.g., 'not for read-only analysis' or 'prefer explain_query for understanding query plans'). Effectively absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server