execute_query_read_only
AI agents call execute_query_read_only to retrieve information from Trino MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name strongly implies this tool executes SQL queries in a read-only mode, preventing writes or destructive operations. However, the description is empty, which reduces confidence. Given the server supports arbitrary SQL and 'read-only' constraints are enforced by safety controls, misuse risk is medium — a misconfigured read-only mode could still expose sensitive data at scale.
From the tool's definition Tool name 'execute_query_read_only' suggests a read-only SQL query execution; server description mentions 'read/write operations with safety controls'
Attacks that exploit this kind of access
execute_query_read_only. It is categorised as a Read tool in the Trino MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Trino MCP Server MCP server in PolicyLayer and add a rule for execute_query_read_only: 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_read_only 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_read_only 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_read_only. 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_read_only is provided by the Trino MCP Server MCP server (weijie-tan3/trino-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →