AI agents call inspect_table 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.
This tool retrieves metadata (schema, columns, types, constraints) from a table without querying data, executing code, or modifying anything. It is a read-only introspection operation. The low severity reflects minimal blast radius—metadata disclosure alone poses limited immediate risk compared to data exfiltration or query execution tools on this server.
From the tool's definition Tool name 'inspect_table' and description 'Get detailed metadata about a table' indicate retrieval of table structure and schema information only, with no modification or side effects.
Documented attack patterns abuse exactly the kind of access inspect_table 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 inspect_table:
{
"version": "1",
"default": "deny",
"tools": {
"inspect_table": {}
}
}inspect_table 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.
Get detailed metadata about a table. 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 inspect_table: 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.
inspect_table 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 inspect_table 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 inspect_table. 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.
inspect_table 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.