Perform multiple Google searches in parallel
AI agents call parallel_search to retrieve information from MCP Deep Web Research Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves search results from Google without creating, modifying, deleting, or executing anything. Multiple parallel searches are still read operations—they query and return information with no side effects. The severity is low because misuse would at worst return unwanted search results, with no capability to harm systems, data, or finances.
From the tool's definition Tool description states: 'Perform multiple Google searches in parallel'. Google search is a read-only information retrieval operation that queries publicly available data without modification or execution of arbitrary code.
Attacks that exploit this kind of access
Perform multiple Google searches in parallel. It is categorised as a Read tool in the MCP Deep Web Research Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Deep Web Research Server MCP server in PolicyLayer and add a rule for parallel_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 Deep Web Research Server. Nothing to install.
parallel_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 parallel_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 parallel_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.
parallel_search is provided by the MCP Deep Web Research Server MCP server (pedrodnt/mcp-deepwebresearch). 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 →