// MCP TOOL REFERENCE

PG TOOLS

5 tools from the Pg MCP Server, categorised by risk level.

View the Pg policy →
// ALL 5 PG TOOLS
READ 2 tools
Read pg_metadata Analyzes a SQL query and produces visualization metadata. Args: conn_id: Conne... Read pg_query Execute a read-only SQL query against the PostgreSQL database. Args: query: Th...
WRITE 2 tools
Write connect Register a database connection string and return its connection ID. Args: conn... Write disconnect Close a specific database connection and remove it from the pool. Args: conn_i...
EXECUTE 1 tools
Execute pg_explain Execute an EXPLAIN (FORMAT JSON) query to get PostgreSQL execution plan. Args: ...

Route Pg through PolicyLayer and every one of its 5 tools is checked against your policy before it runs.

GOVERN PG →

Enforced before the call runs. Nothing to install.

// FAQ
How many tools does the Pg MCP server have? +

The Pg MCP server exposes 5 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Pg tools? +

Route the Pg server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Pg tools fall into? +

Pg tools are categorised as Read (2), Write (2), Execute (1). Each category has a recommended default policy.

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.

GOVERN PG →

Free to start. No card required.

42,500+ MCP servers and 110,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.