AI agents call perplexity_search to retrieve information from VibeServe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web search is a read-only operation that retrieves information. It has no capacity to modify data, execute code, trigger external operations with side effects, delete information, or commit financial transactions. The blast radius of misuse is minimal — an agent could retrieve sensitive information or perform reconnaissance, but cannot directly damage systems or data.
From the tool's definition Tool description states 'Search the web via Perplexity AI' — a retrieval operation with no side effects. The action is querying external data sources without modifying, deleting, or executing code.
Attacks that exploit this kind of access
Search the web via Perplexity AI. It is categorised as a Read tool in the VibeServe MCP Server, which means it retrieves data without modifying state.
Register the VibeServe MCP server in PolicyLayer and add a rule for perplexity_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 VibeServe. Nothing to install.
perplexity_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 perplexity_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 perplexity_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.
perplexity_search is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →