Search the web using Brave Search API.
AI agents call brave_search to retrieve information from Weather MCP 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 the web via an API. Search operations are read-only with no side effects—they query external data sources and return results without modifying, deleting, or executing code. The lack of parameters that suggest result modification or command execution (such as filter_unsafe=false or execute_actions) further supports the Read classification.
From the tool's definition Tool name 'brave_search' and description 'Search the web using Brave Search API' indicate query-only functionality that retrieves information without creating, modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Search the web using Brave Search API. It is categorised as a Read tool in the Weather MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Weather MCP Server MCP server in PolicyLayer and add a rule for brave_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 Weather MCP Server. Nothing to install.
brave_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 brave_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 brave_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.
brave_search is provided by the Weather MCP Server MCP server (roblopez-qz/mcp-hack). 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 →