AI agents call 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 retrieves and returns search results without modifying any data, triggering side effects, executing code, deleting content, or moving money. Despite the empty description, the naming convention and context (batch_search_google sibling, Google search integration mentioned in server description) strongly indicate this is a read-only query tool.
From the tool's definition Tool is named 'search_google' and is part of a server focused on 'content extraction and analysis' with 'Google search integration'.
Documented attack patterns abuse exactly the kind of access 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 search_google:
{
"version": "1",
"default": "deny",
"tools": {
"search_google": {}
}
}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.
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 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.
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 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 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.
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.