Fuzzy-match a term against all column names; return top hits.
AI agents call search_schema 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 retrieves schema information (column names) through a search operation without side effects. It is purely informational—similar to a metadata query. The fuzzy-matching and ranking of results are read-only operations that do not alter data, execute code, or trigger external operations.
From the tool's definition Tool performs 'fuzzy-match' search and 'return top hits' against schema metadata; no modification, deletion, or execution of queries described.
Attacks that exploit this kind of access
Fuzzy-match a term against all column names; return top hits. 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 search_schema: 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.
search_schema 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 search_schema 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 search_schema. 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.
search_schema 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.
search_schema is one line of Mcp Bigquery Evals's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →