AI agents call search_brave_with_summary to retrieve information from MCP2Brave 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 the Brave Search API. It has no side effects, does not modify any data, execute code, or trigger external operations beyond read-only API queries. Web search is a standard information retrieval operation with minimal security risk when misused by an AI agent—the worst outcome would be irrelevant or spam results. It belongs in the Read category with low severity.
From the tool's definition Tool name 'search_brave_with_summary' and description 'Search the web using Brave Search API' indicate a retrieval operation that queries web search results without modifying data or executing code.
Attacks that exploit this kind of access
Search the web using Brave Search API. It is categorised as a Read tool in the MCP2Brave MCP Server, which means it retrieves data without modifying state.
Register the MCP2Brave MCP server in PolicyLayer and add a rule for search_brave_with_summary: 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 MCP2Brave. Nothing to install.
search_brave_with_summary 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_brave_with_summary 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_brave_with_summary. 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_brave_with_summary is provided by the MCP2Brave MCP server (mcp2everything/mcp2brave). 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 →