Get AI-powered answers with citations and reasoning. Use when you need synthesized answers rather than raw search results. Providers: kagi_fastgpt (fast ~900ms answers), exa_answer (semantic AI), linkup (deep agentic search with sources).
AI agents call ai_search to retrieve information from Mcp Omnisearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and synthesizes information from search providers to generate answers. It is fundamentally a read operation—querying external sources and returning processed results. There are no indications of write, execute, destructive, or financial capabilities. The 'AI-powered' aspect refers to answer synthesis, not arbitrary code execution.
From the tool's definition Tool description explicitly states 'Get AI-powered answers with citations and reasoning' and lists search/answer providers (kagi_fastgpt, exa_answer, linkup).
Attacks that exploit this kind of access
Get AI-powered answers with citations and reasoning. Use when you need synthesized answers rather than raw search results. Providers: kagi_fastgpt (fast ~900ms answers), exa_answer (semantic AI), linkup (deep agentic search with sources). It is categorised as a Read tool in the Mcp Omnisearch MCP Server, which means it retrieves data without modifying state.
Register the Mcp Omnisearch MCP server in PolicyLayer and add a rule for ai_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 Omnisearch. Nothing to install.
ai_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 ai_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 ai_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.
ai_search is provided by the Mcp Omnisearch MCP server (mcp-omnisearch). 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 →