run_sql

THE RISK

High Risk

This tool executes SQL queries with effects that depend entirely on the SQL statement provided. While it *could* be used for safe read operations, it also permits destructive operations (DROP TABLE, DELETE, TRUNCATE) and Write operations (INSERT, UPDATE) without apparent restrictions mentioned in the description.

From the tool's definition Tool name 'run_sql' with description 'Execute SQL operations on a connected workspace' indicates arbitrary SQL execution capability.

Documented attack patterns abuse exactly the kind of access run_sql gives an agent:

HOW TO CONTROL RUN_SQL

PolicyLayer is an MCP gateway — it sits between your AI agents and SingleStore MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_sql:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_sql": {
      "limits": [
        {
          "counter": "run_sql_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

run_sql stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register SingleStore MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More SingleStore MCP Server tools

Destructive delete_job Delete an existing job Destructive stage_delete Delete a file or folder from Stage Destructive terminate_starter_workspace Terminate an existing starter workspace Execute create_job_from_notebook Create a scheduled job from a notebook Execute resume_workspace Resume a suspended workspace Write choose_organization Choose from available organizations (only available when API key environment variable is n Write create_notebook_file Create a new notebook file in SingleStore Spaces Write create_starter_workspace Create a new starter workspace

All 24 SingleStore MCP Server tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in SingleStore MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the run_sql tool do? +

Execute SQL operations on a connected workspace. It is categorised as a Execute tool in the SingleStore MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_sql? +

Register the SingleStore MCP Server MCP server in PolicyLayer and add a rule for run_sql: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches SingleStore MCP Server. Nothing to install.

What risk level is run_sql? +

run_sql is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_sql? +

Yes. Add a rate_limit block to the run_sql rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block run_sql completely? +

Set action: deny in the PolicyLayer policy for run_sql. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides run_sql? +

run_sql is provided by the SingleStore MCP Server MCP server (singlestore-labs/mcp-server-singlestore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SingleStore MCP Server tool call.

Deterministic rules across all 24 SingleStore MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN SINGLESTORE →

Free to start. No card required.

24 SingleStore MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT RUN_SQL ON SINGLESTORE MCP SERVER DOES

// THE RISK

// HOW TO CONTROL RUN_SQL

// EXPLORE