// SCAN REPORT

Postgres

8 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 1 Sept 2026

3 can modify or destroy data

5 read-only

8 tools total

Community server · catalogue entry checked 01/09/2026 · full schemas captured for 6 of 8 tools

How to control Postgres ↓

TOOL MAP

What Postgres exposes to your agents

Read (5) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Postgres costs in tokens

833 tokens of tool definitions, loaded on every request

0.4% of a 200k context window

182 heaviest tool: run_query

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Postgres tools

Execute · High run_query Execute a read-only SELECT query and return structured rows (FR-003) Execute · High run_write_query Execute INSERT/UPDATE/DELETE/DDL statements when write mode is enabled (FR-006) Write · Medium set_role Set active PostgreSQL role/user for the session (SET ROLE) or reset to default (RESET ROLE)

3 of Postgres's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Postgres

PolicyLayer is an MCP gateway — it sits between your AI agents and Postgres, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "set_role": {
    "limits": [
      {
        "counter": "set_role_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "describe_table": {
    "limits": [
      {
        "counter": "describe_table_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Postgres — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON POSTGRES →

Instant setup, no code required.

FULL CATALOGUE

All 8 Postgres tools

EXECUTE 2 tools

Execute run_query Execute a read-only SELECT query and return structured rows (FR-003) Execute run_write_query Execute INSERT/UPDATE/DELETE/DDL statements when write mode is enabled (FR-006)

WRITE 1 tools

Write set_role Set active PostgreSQL role/user for the session (SET ROLE) or reset to default (RESET ROLE)

READ 5 tools

Read describe_table Detail the columns, types, and primary keys of a specific table (FR-002) Read list_databases Discover databases visible/connectable to the connected user (FR-002a) Read list_permissions Discover privileges granted to roles on schemas, tables, and columns (FR-002c) Read list_roles Discover roles/users and their attributes and memberships (FR-002b) Read list_tables Discover schemas and their tables/columns without writing a query (FR-002)

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Postgres

How do I prevent bulk modifications through Postgres? +

The Postgres server has 1 write tools including set_role. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Postgres.

How many tools does the Postgres MCP server expose? +

8 tools across 3 categories: Execute, Read, Write. 5 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Postgres? +

Register the Postgres MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Postgres tool call.

Deterministic rules across all 8 Postgres tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON POSTGRES →

Instant setup, no code required.

8 Postgres tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Postgres's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →