AI agents call get_announcements to retrieve information from Rohlik without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves announcements and notifications—read-only operations with no side effects. There is no data creation, modification, deletion, code execution, or financial transaction involved. The blast radius of misuse is minimal, as an attacker could only access notification information that is likely intended to be public or accessible to the user account.
From the tool's definition Tool name 'get_announcements' and description 'Get current announcements and notifications from Rohlik' both indicate retrieval of existing data with no modification, deletion, or execution of operations.
Attacks that exploit this kind of access
Get current announcements and notifications from Rohlik. It is categorised as a Read tool in the Rohlik MCP Server, which means it retrieves data without modifying state.
Register the Rohlik MCP server in PolicyLayer and add a rule for get_announcements: 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 Rohlik. Nothing to install.
get_announcements 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_announcements 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_announcements. 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_announcements is provided by the Rohlik MCP server (@tomaspavlin/rohlik-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 →