Performs a comprehensive web search using Google Custom Search API, fetching the FULL content from top results using advanced content extraction (Readability algorithm), and returning consolidated content. Supports web, news, and image search types. Includes retry logic for reliability.
AI agents call deep_search to retrieve information from Google Search MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries external web content and extracts information via the Google Custom Search API and Readability algorithm. It has no side effects on any data source — it only reads and reformats publicly available web pages. The retry logic mentioned is for reliability, not for side effects.
From the tool's definition Tool description explicitly states it 'Performs a comprehensive web search' and 'fetching the FULL content from top results' — purely retrieval operations. No write, execute, destructive, or financial operations are mentioned.
Attacks that exploit this kind of access
Performs a comprehensive web search using Google Custom Search API, fetching the FULL content from top results using advanced content extraction (Readability algorithm), and returning consolidated content. Supports web, news, and image search types. Includes retry logic for reliability. It is categorised as a Read tool in the Google Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Search MCP Server MCP server in PolicyLayer and add a rule for deep_search: 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 Google Search MCP Server. Nothing to install.
deep_search 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 deep_search 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 deep_search. 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.
deep_search is provided by the Google Search MCP Server MCP server (thejusdutt/google-search-mcp). 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 →