AI agents use mark_thread_addressed to create or update resources in Yocoolab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yocoolab environment.
This tool creates or modifies data reversibly: it changes the status of a feedback thread to 'resolved' and optionally appends a message. These actions are reversible (a thread can be reopened or a message deleted), making it a Write operation rather than Destructive.
From the tool's definition Tool description states it 'Mark[s] a feedback thread as resolved' and can 'Optionally add a message', which modifies the state of a feedback thread and potentially adds data to it.
Attacks that exploit this kind of access
Mark a feedback thread as resolved. Optionally add a message explaining how it was addressed. It is categorised as a Write tool in the Yocoolab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Yocoolab MCP server in PolicyLayer and add a rule for mark_thread_addressed: 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.
mark_thread_addressed 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 mark_thread_addressed 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 mark_thread_addressed. 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.
mark_thread_addressed 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 →