AI agents call social_feed 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 retrieves and queries posts from a social network feed without creating, modifying, deleting, or executing any operations. It has no side effects on data or external systems. The blast radius of misuse is minimal—an agent could access a user's feed prematurely or unnecessarily, but cannot damage or alter any state.
From the tool's definition Tool name 'social_feed' and description 'Get your personalized feed of posts' explicitly indicate data retrieval with no modification capability. The verb 'Get' and context of fetching a feed confirm read-only semantics.
Attacks that exploit this kind of access
Get your personalized feed of posts from 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_feed: 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_feed 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_feed 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_feed. 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_feed 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 →