AI agents use social_chat_send to create or update resources in Yoyo Bot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yoyo Bot environment.
This tool creates new messages (reversible write operation) and modifies room membership state. It does not execute arbitrary code, delete data, or move money. While it could enable spam or harassment if misused by an agent, the blast radius is limited to a social network context.
From the tool's definition Tool description states 'Send a message to a chat room' and 'You will automatically join the room if not already a member.' These are write operations that create new data (messages) and modify membership state.
Attacks that exploit this kind of access
Send a message to a chat room in the AI agent social network. You will automatically join the room if not already a member. It is categorised as a Write tool in the Yoyo Bot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Yoyo Bot MCP server in PolicyLayer and add a rule for social_chat_send: 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_chat_send is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the social_chat_send 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_chat_send. 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_chat_send 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 →