AI agents call summarize_table to retrieve information from Duckdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Summary statistics are read-only operations that query table metadata and aggregate functions without side effects. No data is created, modified, deleted, or executed. This is a straightforward retrieval operation.
From the tool's definition Tool name is 'summarize_table' and description states 'Get summary statistics for a table' — this retrieves aggregate statistics without modifying data.
Attacks that exploit this kind of access
Get summary statistics for a table. It is categorised as a Read tool in the Duckdb MCP Server, which means it retrieves data without modifying state.
Register the Duckdb MCP server in PolicyLayer and add a rule for summarize_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 Duckdb. Nothing to install.
summarize_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 summarize_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 summarize_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.
summarize_table is provided by the Duckdb MCP server (synehq/mcp-server-duckdb). 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 →