AI agents call handle_inspect_table to retrieve information from Redshift Utils without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'inspect_table' strongly implies a read operation — examining table structure, statistics, or metadata — similar to sibling tools like 'handle_get_table_definition'. No evidence of write, execute, or destructive capability. Confidence is reduced due to empty description. Severity is medium because table inspection on a Redshift cluster could expose sensitive schema information.
From the tool's definition Tool name 'handle_inspect_table' suggests reading/querying table metadata or structure. Description is empty, providing no additional context.
Documented attack patterns abuse exactly the kind of access handle_inspect_table gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Redshift Utils, and nothing reaches the server without passing your rules. This is the rule we recommend for handle_inspect_table:
{
"version": "1",
"default": "deny",
"tools": {
"handle_inspect_table": {}
}
}handle_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.
handle_inspect_table. It is categorised as a Read tool in the Redshift Utils MCP Server, which means it retrieves data without modifying state.
Register the Redshift Utils MCP server in PolicyLayer and add a rule for handle_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 Redshift Utils. Nothing to install.
handle_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 handle_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 handle_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.
handle_inspect_table is provided by the Redshift Utils MCP server (vinodismyname/redshift-utils-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Redshift Utils, 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.
7 Redshift Utils tools catalogued and risk-classified — across an index of 43,000+ MCP servers.