List all messages left unread since the user last read each room in
AI agents call get_unread to retrieve information from Rocket Cli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries unread message information from Rocket.Chat, displaying data without side effects. It follows the pattern of other sibling tools like get_messages, get_mentions, and get_thread_messages which are all Read operations. The action is purely informational—listing unread messages does not modify, delete, or trigger external operations.
From the tool's definition Tool name 'get_unread' and description 'List all messages left unread since the user last read each room' indicate a retrieval operation with no modification or deletion of data.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
List all messages left unread since the user last read each room in. It is categorised as a Read tool in the Rocket Cli MCP Server, which means it retrieves data without modifying state.
Register the Rocket Cli MCP server in PolicyLayer and add a rule for get_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 Rocket Cli. Nothing to install.
get_unread 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_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 get_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.
get_unread is provided by the Rocket Cli MCP server (jeanfbrito/rocket-cli). 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 →