Skip to main content
Glama
antonorlov

MCP PostgreSQL Server

by antonorlov
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Run a write statement (disabled)

execute
Destructive

Run INSERT, UPDATE, DELETE, or DDL statements against PostgreSQL. Requires the server to be started with PG_ALLOW_WRITE=true; otherwise, it returns an error and makes no changes.

Instructions

Run a data-modifying SQL statement (INSERT/UPDATE/DELETE or DDL). Currently DISABLED: the server is read-only, so this returns an error and changes nothing. To enable writes, the operator must start the server with PG_ALLOW_WRITE=true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sqlYesOne INSERT / UPDATE / DELETE / DDL statement. Use $1, $2, ... for parameters.
paramsNoPositional parameter values bound to $1, $2, ... placeholders.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.3.0
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / params / description
      Previous value: -"Query parameters (optional)"New value: +"Positional parameter values bound to $1, $2, ... placeholders."
    • changedInput schema / properties / sql / description
      Previous value: -"SQL query (INSERT, UPDATE, DELETE) (use $1, $2, etc. for parameters)"New value: +"One INSERT / UPDATE / DELETE / DDL statement. Use $1, $2, ... for parameters."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Adds critical context beyond annotations: it returns an error and changes nothing due to the server being read-only, and explains how to enable writes. This is transparent and consistent with destructiveHint=true and readOnlyHint=false—no contradiction.

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

Conciseness5/5

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

Two concise sentences that front-load the purpose, then immediately disclose the disabled state and the fix. No wasted words, and the structure is logical.

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

Completeness4/5

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

For a disabled write tool with no output schema, the description fully explains current behavior and the enabling condition. It doesn't describe success response when enabled, but that's irrelevant given the disabled state; the agent knows calling it will fail now.

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

Parameters3/5

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

Schema description covers both parameters fully (sql statement and positional params), including the placeholder syntax. The description restates the statement type but adds no new parameter semantics beyond what the schema already provides, so baseline 3 is appropriate.

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

Purpose5/5

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

The description explicitly states it runs data-modifying SQL (INSERT/UPDATE/DELETE/DDL), which distinguishes it from sibling tools like query and describe_table. It also indicates the tool is currently disabled, adding precise scope.

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

Usage Guidelines4/5

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

It clearly says the tool is disabled, explains the server read-only condition, and gives the exact flag needed to enable it (PG_ALLOW_WRITE=true). This provides strong when-not-to-use guidance, though it doesn't explicitly name alternatives like query for read operations.

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

Deploy Server

Other Tools