AI web search optimized for agents. Returns ranked results with the relevant extracted content of each page (not just a link + blurb), plus a relevance score. topic=news for recent reporting. Distinct from search.web (raw SERP) — this returns clean, LLM-ready page content per result.
AI agents call search.ai to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search.ai is a read-only tool that retrieves and processes publicly available web content for ranking and extraction purposes. It has no capability to modify, delete, or execute actions on external systems. While it is a paid service via x402 (a financial transaction occurs at the protocol level, not as a direct tool action), the tool itself only performs data retrieval.
From the tool's definition The tool description states it 'Returns ranked results with the relevant extracted content of each page' and 'returns clean, LLM-ready page content per result.' These operations are information retrieval with no modification of data or external side effects…
Attacks that exploit this kind of access
AI web search optimized for agents. Returns ranked results with the relevant extracted content of each page (not just a link + blurb), plus a relevance score. topic=news for recent reporting. Distinct from search.web (raw SERP) — this returns clean, LLM-ready page content per result. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for search.ai: 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. Nothing to install.
search.ai 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.ai 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.ai. 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.ai is provided by the MCP server (@2sio/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 →