Execute a read-only SQL query. Only SELECT, WITH, EXPLAIN, SHOW, and VALUES are allowed. Results are limited by the limit parameter.
AI agents call execute-query to retrieve information from Tusk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly restricts execution to read-only SQL statements (SELECT, WITH, EXPLAIN, SHOW, VALUES), preventing any data modification or destructive operations. It retrieves data from the database without side effects. Severity is medium rather than low because arbitrary SELECT queries could expose sensitive data across the entire database if misused.
From the tool's definition Execute a read-only SQL query. Only SELECT, WITH, EXPLAIN, SHOW, and VALUES are allowed.
Documented attack patterns abuse exactly the kind of access execute-query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tusk, and nothing reaches the server without passing your rules. This is the rule we recommend for execute-query:
{
"version": "1",
"default": "deny",
"tools": {
"execute-query": {}
}
}execute-query is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a read-only SQL query. Only SELECT, WITH, EXPLAIN, SHOW, and VALUES are allowed. Results are limited by the limit parameter. It is categorised as a Read tool in the Tusk MCP Server, which means it retrieves data without modifying state.
Register the Tusk MCP server in PolicyLayer and add a rule for 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 Tusk. Nothing to install.
execute-query is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the 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.
Set action: deny in the PolicyLayer policy for 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.
execute-query is provided by the Tusk MCP server (volveezz/tusk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tusk, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Tusk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.