AI agents call batch_search_google to retrieve information from Crawl-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Google search is a read-only operation that retrieves publicly available information without modifying, deleting, or executing code. The 'batch' aspect suggests efficiency but does not change the fundamental nature: querying and retrieving data. No side effects, no code execution, no data modification.
From the tool's definition Tool name 'batch_search_google' and server context indicate Google search integration mentioned in the server description. Despite empty description, the prefix 'batch_' combined with 'search' suggests retrieving search results in bulk.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access batch_search_google gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crawl-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for batch_search_google:
{
"version": "1",
"default": "deny",
"tools": {
"batch_search_google": {}
}
}batch_search_google 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.
batch_search_google. It is categorised as a Read tool in the Crawl-MCP MCP Server, which means it retrieves data without modifying state.
Register the Crawl- MCP server in PolicyLayer and add a rule for batch_search_google: 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 Crawl-MCP. Nothing to install.
batch_search_google 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 batch_search_google 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 batch_search_google. 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.
batch_search_google is provided by the Crawl- MCP server (walksoda/crawl-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 Crawl-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
19 Crawl-MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.