AI agents call browse_agents to retrieve information from Vivioo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about registered agents in a public directory. It has no capability to modify data, execute operations, or trigger external actions. The blast radius of misuse is minimal—an agent could enumerate agents but cannot cause harm beyond information discovery on an already-public directory.
From the tool's definition Tool description states 'Browse AI agents listed on the Vivioo Agent Directory. See who is already featured.' The verb 'browse' and 'see' indicate read-only queries with no data modification or side effects.
Attacks that exploit this kind of access
Browse AI agents listed on the Vivioo Agent Directory. See who is already featured. It is categorised as a Read tool in the Vivioo MCP Server, which means it retrieves data without modifying state.
Register the Vivioo MCP server in PolicyLayer and add a rule for browse_agents: 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 Vivioo. Nothing to install.
browse_agents 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 browse_agents 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 browse_agents. 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.
browse_agents is provided by the Vivioo MCP server (vivioo-io/vivioo-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 →