// SCAN REPORT

Pg

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

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

Last updated: 10 Jun 2026

3 can modify or destroy data

2 read-only

5 tools total

Community server · catalogue entry verified 10/06/2026

How to control Pg ↓

TOOL MAP

Read (2) Write / Execute (3) Destructive / Financial (0)

MOST DANGEROUS TOOLS

High Risk

Execute · High pg_explain This tool falls into the Execute category because it triggers external operations on a PostgreSQL database—specifically executing EXPLAIN commands whose effects (performance analysis, resource consumption during planning Write · High connect This tool registers a new database connection, which is a reversible configuration action that persists state in the MCP server's connection registry. Write · Medium disconnect This tool modifies the connection pool state (removes a connection) rather than deleting data.

3 of Pg's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL PG

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

Rate limit write operations

{
  "connect": {
    "limits": [
      {
        "counter": "connect_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "pg_metadata": {
    "limits": [
      {
        "counter": "pg_metadata_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 Pg — 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 PG →

Free to start. No card required.

ALL 5 PG TOOLS

EXECUTE 1 tools

Execute pg_explain Execute an EXPLAIN (FORMAT JSON) query to get PostgreSQL execution plan. Args: qu

WRITE 2 tools

Write connect Register a database connection string and return its connection ID. Args: connect Write disconnect Close a specific database connection and remove it from the pool. Args: conn_id:

READ 2 tools

Read pg_metadata Analyzes a SQL query and produces visualization metadata. Args: conn_id: Connecti Read pg_query Execute a read-only SQL query against the PostgreSQL database. Args: query: The S

RELATED SERVERS

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

FAQ

How do I prevent bulk modifications through Pg? +

The Pg server has 2 write tools including connect, disconnect. 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 Pg.

How many tools does the Pg MCP server expose? +

5 tools across 3 categories: Execute, Read, Write. 2 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Pg? +

Register the Pg 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 Pg tool call.

Deterministic rules across all 5 Pg tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PG →

Free to start. No card required.

5 Pg tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Pg

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL PG

// ALL 5 PG TOOLS

// RELATED SERVERS

// FAQ