AI agents call brave_web_search to retrieve information from Mcp Nexus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries external search data and returns read-only results. There is no data modification, deletion, code execution, financial transaction, or irreversible action. The only consideration is potential information disclosure or reconnaissance risks, but these are inherent to any search capability and represent low severity in an MCP context.
From the tool's definition Tool name 'brave_web_search' and description explicitly states it 'Performs a web search' and 'Returns a JSON array of results' — retrieval only with no side effects.
Attacks that exploit this kind of access
Performs a web search using the Brave Search API. Use for general web searches for information, facts, and current topics. Returns a JSON array of results. It is categorised as a Read tool in the Mcp Nexus MCP Server, which means it retrieves data without modifying state.
Register the Mcp Nexus MCP server in PolicyLayer and add a rule for brave_web_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 Nexus. Nothing to install.
brave_web_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_web_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_web_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_web_search is provided by the Mcp Nexus MCP server (xydong-web/mcp-nexus). 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 →