Return up to n sample rows from a table.
AI agents call sample_table to retrieve information from Mcp Bigquery Evals without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves a limited subset of data from a table. It is a read-only operation with no side effects, no data modification, no execution of code, and no irreversible actions. The 'up to n' constraint further limits scope. The server's mandatory cost guardrails and dry-run behavior provide additional safety.
From the tool's definition Tool name 'sample_table' and description 'Return up to n sample rows from a table' indicate retrieval of data with no modification or deletion.
Attacks that exploit this kind of access
Return up to n sample rows from a table. It is categorised as a Read tool in the Mcp Bigquery Evals MCP Server, which means it retrieves data without modifying state.
Register the Mcp Bigquery Evals MCP server in PolicyLayer and add a rule for sample_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 Mcp Bigquery Evals. Nothing to install.
sample_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 sample_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 sample_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.
sample_table is provided by the Mcp Bigquery Evals MCP server (umarfarook1/mcp-bigquery-evals). 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 →