Skip to main content
Glama
Sign In
MCPg - Production-grade PostgreSQL MCP Server

MCPg - Production-grade PostgreSQL MCP Server

by devopam
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Read PG stat IO

read_pg_stat_io
Read-only

Reads PostgreSQL 16+ pg_stat_io to report cumulative I/O by backend type, object, and context, helping identify buffer-cache misses and write amplification.

Instructions

Read the pg_stat_io view (PostgreSQL 16+). Reports per (backend_type, object, context) cumulative I/O activity — reads, writes, extends, evictions, hits, fsyncs. Useful for spotting buffer-cache misses and write amplification. On PostgreSQL 14 / 15 the view doesn't exist, so the tool returns available=false and an empty list.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "read_pg_stat_io"
  }
}

Input Schema

NameRequiredDescriptionDefault
databaseNoOptional: a database id from list_databases, to target a configured secondary (read-only) database; omit for the primary. Database names that are not configured ids are rejected.

Output Schema

NameRequiredDescriptionDefault
rowsYes
availableYes
server_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.4
    • changedInput schema / properties / database / description
      Previous value: -"Optional: target a configured secondary (read-only) database by name; omit for the primary. Call list_databases to see the configured ids."New value: +"Optional: a database id from list_databases, to target a configured secondary (read-only) database; omit for the primary. Database names that are not configured ids are rejected."
  2. First observedv0.6.8

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description still adds real behavioral context beyond them: the counters are cumulative, and on unsupported server versions the tool degrades gracefully to available=false plus an empty list rather than erroring — important for interpreting results. It does not discuss reset behavior of cumulative counters or row volume, which keeps it short of a 5.

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?

Three sentences, front-loaded with the resource and version, then the payload, then the failure mode. No filler and no repetition of the title.

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?

With an output schema present, return values needn't be explained, and the version caveat covers the main failure path. Only the database/secondary-targeting behavior is left entirely to the schema, a minor gap for a single-parameter read tool.

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?

There is a single optional parameter (database) with 100% schema description coverage, including the constraint that non-configured names are rejected. The description contributes nothing about targeting a secondary database, so the schema is doing all the work; baseline 3 applies.

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 names the exact resource (the pg_stat_io view, PostgreSQL 16+) and specifies the grouping granularity (backend_type, object, context) plus the metrics reported (reads, writes, extends, evictions, hits, fsyncs). This clearly separates it from nearby siblings like read_pg_buffercache_summary and read_pg_wal_stats without the agent needing to open the schema.

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 states the diagnostic use case — spotting buffer-cache misses and write amplification — and gives an explicit version exclusion: on PostgreSQL 14/15 the view doesn't exist and the tool returns available=false with an empty list. What's missing is routing guidance toward the alternative tools (buffercache summary, WAL stats, recommend_io_method) when this view is unavailable or when a different granularity is wanted.

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