AI agents call web.rich to retrieve information from Earch MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves web search results through the Brave Search API. The description indicates it fetches and returns data (rich search results) without creating, modifying, deleting data, or executing arbitrary code. It is purely a read operation with minimal blast radius if misused—worst case being excessive API calls or information leakage through search queries.
From the tool's definition Tool performs 'Brave Rich Search' data retrieval with 'fetches rich data' - a query operation that retrieves search results without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Brave Rich Search via callback flow. First enables rich callback, then fetches rich data. It is categorised as a Read tool in the Earch MCP MCP Server, which means it retrieves data without modifying state.
Register the Earch MCP server in PolicyLayer and add a rule for web.rich: 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 Earch MCP. Nothing to install.
web.rich 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 web.rich 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 web.rich. 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.
web.rich is provided by the Earch MCP server (nanameru/search-mcp). 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 →