Mark a chat as unread.
AI agents use mark_chat_unread to create or update resources in Bluebubbles — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bluebubbles environment.
The tool updates the read status of a chat, which is a reversible modification operation. While it changes state, it does not delete data (would be Destructive), execute code (Execute), send financial transactions (Financial), or perform I/O beyond metadata updates. The low severity reflects minimal blast radius—an accidental misuse would only toggle chat visibility state, easily reversible by the user.
From the tool's definition Tool description: 'Mark a chat as unread.' This modifies chat metadata (read/unread state) reversibly without deleting data or executing arbitrary code.
Attacks that exploit this kind of access
Mark a chat as unread. It is categorised as a Write tool in the Bluebubbles MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bluebubbles MCP server in PolicyLayer and add a rule for mark_chat_unread: 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 Bluebubbles. Nothing to install.
mark_chat_unread 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_chat_unread 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_chat_unread. 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_chat_unread is provided by the Bluebubbles MCP server (metaember/bluebubbles-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 →