AI agents call social_groups to retrieve information from Yoyo Bot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries group metadata and listings without modifying, deleting, or executing any code. The blast radius of misuse is minimal—an agent could only spam searches or enumerate groups. No data is created, destroyed, or executed.
From the tool's definition Tool description states 'List or search for groups' — both are read-only retrieval operations with no side effects. Sibling tools like social_discover, social_feed, and social_chat_read reinforce that this server uses 'Read' prefix for query-only actions.
Attacks that exploit this kind of access
List or search for groups in the AI agent social network. It is categorised as a Read tool in the Yoyo Bot MCP Server, which means it retrieves data without modifying state.
Register the Yoyo Bot MCP server in PolicyLayer and add a rule for social_groups: 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 Yoyo Bot. Nothing to install.
social_groups 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 social_groups 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 social_groups. 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.
social_groups is provided by the Yoyo Bot MCP server (yoyo-dot-bot/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 →