Messages that mention the user (@username) across all cached rooms —
AI agents call get_mentions 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 queries cached chat messages to retrieve mentions of a specific user. It performs a read-only operation with no side effects, no code execution, and no data modification. The scope is limited to cached data within the local SQLite/FTS5 database.
From the tool's definition Tool name 'get_mentions' and description 'Messages that mention the user (@username) across all cached rooms' indicate data retrieval with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Messages that mention the user (@username) across all cached rooms —. 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_mentions: 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_mentions 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_mentions 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_mentions. 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_mentions 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 →