AI agents invoke execute_query to trigger actions in Trino MCP Server. 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.
execute_query on a distributed SQL engine can run arbitrary queries including those with side effects (INSERT, UPDATE, or when combined with sibling tool cancel_query, suggests full query lifecycle control). While the server description emphasizes 'query and analyze,' SQL engines typically allow write operations unless explicitly restricted.
From the tool's definition Tool named 'execute_query' on a Trino MCP Server that 'enables LLMs to directly query and analyze data stored in Trino databases.' The description is empty, but the name and server context indicate arbitrary SQL execution capability.
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 Trino MCP Server, 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": {
"limits": [
{
"counter": "execute_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
execute_query. It is categorised as a Execute tool in the Trino MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Trino MCP Server 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 Trino MCP Server. Nothing to install.
execute_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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 Trino MCP Server MCP server (stinkgen/trino_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Trino MCP Server, 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.
3 Trino MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.