// SCAN REPORT

MCP SQL Agent

5 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 1 Jul 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 01/07/2026

How to control MCP SQL Agent ↓

TOOL MAP

What MCP SQL Agent exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP SQL Agent tools

Execute · High query_data This tool executes arbitrary SQL queries, which can include not just SELECT statements but potentially INSERT, UPDATE, DELETE, or even DROP depending on what 'safely' restricts.

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

POLICY

How to control MCP SQL Agent

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

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 MCP SQL Agent — 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 MCP SQL AGENT →

Instant setup, no code required.

FULL CATALOGUE

All 5 MCP SQL Agent tools

EXECUTE 1 tools

Execute query_data Execute SQL queries safely. Use get_schema() first to understand the database structure.

READ 4 tools

Read describe_table Get detailed information about a specific table including columns and sample data Read get_schema Get the complete database schema with table structures and sample data Read list_tables List all tables in the database Read search_tables Search for tables or columns containing a specific keyword

FAQ

Questions about MCP SQL Agent

Is the MCP SQL Agent MCP server safe to use without restrictions? +

The MCP SQL Agent server is primarily read-only with 4 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the MCP SQL Agent MCP server expose? +

5 tools across 1 categories: Read. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on MCP SQL Agent? +

Register the MCP SQL Agent 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 MCP SQL Agent tool call.

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

ENFORCE POLICY ON MCP SQL AGENT →

Instant setup, no code required.

5 MCP SQL Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.