mcp_execute_query · Mcpql MCP: Risk & Policy

WHAT IT DOES

What mcp_execute_query does on Mcpql

AI agents invoke mcp_execute_query to trigger actions in Mcpql. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why mcp_execute_query needs a policy

This tool executes arbitrary SQL queries whose effects depend entirely on the input provided. While the description does not explicitly mention DELETE, DROP, or other destructive operations, raw SQL execution is inherently capable of any operation (SELECT, INSERT, UPDATE, DELETE, DROP, etc.). The most common and dangerous misuse would be data exfiltration or destructive operations.

From the tool's definition Tool name 'mcp_execute_query' and description 'Execute a raw SQL query and return the results' explicitly indicate arbitrary SQL execution capability. The phrase 'raw SQL query' means the tool accepts unvalidated SQL input.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mcp_execute_query Rate-limited

mcp_execute_query 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcpql, so you can run agents against it safely.

FAQ

Questions about mcp_execute_query

What does the mcp_execute_query tool do? +

Execute a raw SQL query and return the results. It is categorised as a Execute tool in the Mcpql MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mcp_execute_query? +

Register the Mcpql MCP server in PolicyLayer and add a rule for mcp_execute_query: 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 Mcpql. Nothing to install.

What risk level is mcp_execute_query? +

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

Can I rate-limit mcp_execute_query? +

Yes. Add a rate_limit block to the mcp_execute_query 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 mcp_execute_query completely? +

Set action: deny in the PolicyLayer policy for mcp_execute_query. 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 mcp_execute_query? +

mcp_execute_query is provided by the Mcpql MCP server (mcpql). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.