AI agents call get_ai_conversations to retrieve information from Yocoolab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query operation that retrieves conversation metadata from the Yocoolab design feedback system. It has no side effects, makes no modifications to data, and poses minimal risk if misused by an AI agent. The worst-case scenario is information disclosure of conversation identifiers and associated page URLs, which is a low-severity concern in a design feedback context.
From the tool's definition Tool description states it 'List[s] recent AI assistant conversations' and 'Returns conversation IDs, page URLs, and message counts' — purely retrieves and queries existing conversation metadata without modifying or executing anything.
Attacks that exploit this kind of access
List recent AI assistant conversations. Returns conversation IDs, page URLs, and message counts. It is categorised as a Read tool in the Yocoolab MCP Server, which means it retrieves data without modifying state.
Register the Yocoolab MCP server in PolicyLayer and add a rule for get_ai_conversations: 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 Yocoolab. Nothing to install.
get_ai_conversations 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 get_ai_conversations 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 get_ai_conversations. 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.
get_ai_conversations is provided by the Yocoolab MCP server (yocoolab/mcp-server). 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 →