Open any Rocket.Chat URL the user pastes — a message link, thread,
AI agents invoke open_url to trigger actions in Rocket Cli. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Opening a URL is an external operation that goes beyond simple data retrieval — it triggers navigation or loading of a resource in an external system (Rocket.Chat). This falls under Execute as it performs an action whose effects depend on the URL argument. Severity is medium because a malicious URL could trigger unintended actions within Rocket.Chat, though the blast radius is limited to the Rocket.Chat environment.
From the tool's definition Open any Rocket.Chat URL — triggers an external operation (opening/navigating to a URL) whose effects depend on the argument provided
Attacks that exploit this kind of access
Open any Rocket.Chat URL the user pastes — a message link, thread,. It is categorised as a Execute tool in the Rocket Cli MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Rocket Cli MCP server in PolicyLayer and add a rule for open_url: 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.
open_url is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open_url 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 open_url. 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.
open_url 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 →