@yawlabs/postgres-mcp

Run read-only SQL

pg_readonly

Read-onlyIdempotent

Run SQL without changing data. Executes every statement in a BEGIN READ ONLY transaction, so Postgres rejects writes and rolls back, and is safe for SELECT, EXPLAIN, and SHOW.

Instructions

Run a SQL statement with no persistent data changes. Always executes inside a BEGIN READ ONLY transaction regardless of ALLOW_WRITES, so postgres itself rejects any INSERT/UPDATE/DELETE/DDL and the transaction is always rolled back. Use this whenever the goal is to read - SELECT, EXPLAIN, SHOW, VALUES, WITH ... SELECT, etc. Scope caveat for hosts that auto-allow this tool: READ ONLY constrains writes to the DATABASE, not every side effect. Functions whose effect is outside the table data - pg_cancel_backend / pg_terminate_backend, pg_read_file, lo_export, COPY ... TO PROGRAM - are NOT blocked here and are NOT behind the ALLOW_WRITES gate that pg_kill sits behind. They still require the privileges the DATABASE_URL role holds, so a least-privileged role (e.g. pg_read_all_data) is what actually bounds this tool. Use params for parameterized queries to avoid SQL injection. Params can be strings, numbers, booleans, null, arrays (for postgres arrays / ANY), or objects (for json/jsonb columns). Large result sets are truncated to POSTGRES_MAX_ROWS (default 1000) with a truncated: true flag.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`sql`	Yes	The SQL statement to execute. Hard cap of 1 MB.
`params`	No	Positional parameters referenced as $1, $2, ... in the SQL.

Output Schema

TableJSON Schema

Name	Required	Description
`rows`	Yes	Result rows, capped at POSTGRES_MAX_ROWS. Values are whatever JSON type pg parsed the column into.
`fields`	Yes	Result column descriptors, in select-list order.
`command`	No	Postgres command tag (`INSERT`, `CREATE TABLE`, ...). Absent on the cursor path -- read absence as 'row-returning statement, command unknown'.
`rowCount`	Yes	Rows AFFECTED for DML -- not necessarily rows.length -- and rows returned on the cursor path. Null when pg reported no count.
`truncated`	No	Present and true only when the result hit POSTGRES_MAX_ROWS and rows were dropped.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedv0.12.1Sep 4, 2026
- removedOutput schema / properties / rowCount / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / rowCount / type
```
Added value: +[
+  "number",
+  "null"
+]
```

Changed5 schema fields changedv0.12.0Aug 28, 2026

addedInput schema / $defs

Added value: +{
+  "__schema0": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "number"
+      },
+      {
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      },
+      {
+        "items": {
+          "$ref": "#/$defs/__schema0"
+        },
+        "type": "array"
+      },
+      {
+        "additionalProperties": {
+          "$ref": "#/$defs/__schema0"
+        },
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      }
+    ]
+  }
+}

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

removedInput schema / definitions

Removed value: -{
-  "__schema0": {
-    "anyOf": [
-      {
-        "type": "string"
-      },
-      {
-        "type": "number"
-      },
-      {
-        "type": "boolean"
-      },
-      {
-        "type": "null"
-      },
-      {
-        "items": {
-          "$ref": "#/definitions/__schema0"
-        },
-        "type": "array"
-      },
-      {
-        "additionalProperties": {
-          "$ref": "#/definitions/__schema0"
-        },
-        "propertyNames": {
-          "type": "string"
-        },
-        "type": "object"
-      }
-    ]
-  }
-}

changedInput schema / properties / params / items / $ref

Previous value: -"#/definitions/__schema0"New value: +"#/$defs/__schema0"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "command": {
+      "description": "Postgres command tag (`INSERT`, `CREATE TABLE`, ...). Absent on the cursor path -- read absence as 'row-returning statement, command unknown'.",
+      "type": "string"
+    },
+    "fields": {
+      "description": "Result column descriptors, in select-list order.",
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "dataTypeID": {
+            "type": "number"
+          },
+          "dataTypeName": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "name",
+          "dataTypeID"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "rowCount": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Rows AFFECTED for DML -- not necessarily rows.length -- and rows returned on the cursor path. Null when pg reported no count."
+    },
+    "rows": {
+      "description": "Result rows, capped at POSTGRES_MAX_ROWS. Values are whatever JSON type pg parsed the column into.",
+      "items": {
+        "additionalProperties": {},
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "truncated": {
+      "description": "Present and true only when the result hit POSTGRES_MAX_ROWS and rows were dropped.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "rows",
+    "rowCount",
+    "fields"
+  ],
+  "type": "object"
+}

First observedv0.7.0Jul 29, 2026

TDQS

A5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description adds substantial behavioral detail: transaction rollback semantics, independence from ALLOW_WRITES, unblocked external side-effect functions (pg_cancel_backend, pg_terminate_backend, pg_read_file, lo_export, COPY ... TO PROGRAM), privilege bounding by DATABASE_URL role, and truncation behavior with a truncated flag. This far exceeds what annotations alone provide, and there is 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?

The description is long but every section earns its place: core guarantee, supported statements, dangerous side-effect caveat, parameterization advice, and result truncation. It is front-loaded with the most important behavioral facts and contains no filler or repetition.

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

Completeness5/5

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

Given the complexity of running arbitrary SQL safely, the description is remarkably complete. It covers transaction semantics, side-effect risks, authorization bounds, parameters, and truncation. Since an output schema exists, the description need not explain return values; nothing essential for correct invocation is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real value beyond the schema: it advises using params to avoid SQL injection, explains positional $1/$2 referencing, and maps param types to their postgres semantics (arrays for ANY, objects for json/jsonb). This is genuinely helpful guidance that the schema alone does not convey.

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 opens with a precise, operational definition: run a SQL statement with no persistent data changes inside a BEGIN READ ONLY transaction, with postgres rejecting INSERT/UPDATE/DELETE/DDL. It enumerates supported statement types (SELECT, EXPLAIN, SHOW, VALUES, WITH ... SELECT), making the tool's scope unambiguous and clearly distinguishing it from pg_query.

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

Usage Guidelines5/5

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

It explicitly says to use this tool whenever the goal is to read, and explains that write statements will be rejected by postgres, so the when-not is clear. The scope caveat also names side-effect functions that are NOT blocked and references pg_kill as the sibling tool behind ALLOW_WRITES, giving concrete routing guidance for edge cases.

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

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/YawLabs/postgres-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server