Search Google and get structured results using the SERP API. Performs a Google search and returns the complete JSON response from the API, preserving all available fields and data. Args: query: The search query string. Required. search_type: Type of search to perform. Options: - "search": Regular...
Risk signalsAccepts freeform code/query input (query)
Part of the Mcp Serp server.
Free to start. No card required.
AI agents call serp_google_search to retrieve information from Mcp Serp without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though serp_google_search only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"serp_google_search": {}
}
}See the full Mcp Serp policy for all 11 tools.
These attack patterns abuse exactly the kind of access serp_google_search gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Search Google and get structured results using the SERP API. Performs a Google search and returns the complete JSON response from the API, preserving all available fields and data. Args: query: The search query string. Required. search_type: Type of search to perform. Options: - "search": Regular web search (default) - "images": Image search - "news": News articles - "maps": Map results - "places": Local business/place results - "videos": Video results country: Country code for localized results (e.g., "us", "cn", "uk"). Default is "us". language: Language code for results (e.g., "en", "zh-cn", "fr"). Default is "en". time_range: Time filter for results. Options: - "qdr:h": Past hour - "qdr:d": Past day - "qdr:w": Past week - "qdr:m": Past month - None: No time restriction (default) number: Number of results per page (default: 10). Note: More than 10 results may incur additional credits. page: Page number for pagination (default: 1). Returns: Complete JSON response from the SERP API containing all available data. Example: serp_google_search(query="artificial intelligence", search_type="news"). It is categorised as a Read tool in the Mcp Serp MCP Server, which means it retrieves data without modifying state.
Register the Mcp Serp MCP server in PolicyLayer and add a rule for serp_google_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 Mcp Serp. Nothing to install.
serp_google_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 serp_google_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 serp_google_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.
serp_google_search is provided by the Mcp Serp MCP server (acedatacloud-mcp/mcp-serp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Mcp Serp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.