Read a full Rocket.Chat thread: the parent message plus all its
AI agents call get_thread_messages 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 thread messages from Rocket.Chat without any capability to modify, delete, or execute operations. It is purely a query/fetch operation with no side effects. Severity is low because it only accesses message data that the authenticated user would normally be permitted to read in Rocket.Chat, with no destructive or financial impact.
From the tool's definition Tool name 'get_thread_messages' and description 'Read a full Rocket.Chat thread' explicitly indicates a read operation. The verb 'Read' and the action of retrieving thread messages with no modification capability confirm this is a data retrieval function.
Attacks that exploit this kind of access
Read a full Rocket.Chat thread: the parent message plus all its. 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_thread_messages: 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_thread_messages 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_thread_messages 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_thread_messages. 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_thread_messages 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 →