AI agents call search_metadata to retrieve information from Bq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches metadata according to the server description's mention of 'keyword search' capabilities. Metadata search is a read-only operation that retrieves information without side effects or data modification. Even with an empty tool description, the server's stated purpose and sibling tools (get_datasets, get_tables) strongly indicate this is a non-destructive, query-only function.
From the tool's definition Tool name 'search_metadata' and server description stating it 'retrieves and caches BigQuery metadata (datasets, tables, columns)' indicates data retrieval without modification.
Attacks that exploit this kind of access
search_metadata. It is categorised as a Read tool in the Bq MCP Server, which means it retrieves data without modifying state.
Register the Bq MCP server in PolicyLayer and add a rule for search_metadata: 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 Bq. Nothing to install.
search_metadata 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_metadata 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_metadata. 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_metadata is provided by the Bq MCP server (takada-at/bq_mcp_server). 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 →