AI agents call baseline_get_announcements to retrieve information from Baseline without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static notification announcements from the vendor with no side effects. It is a straightforward data query operation that returns informational content. The low severity reflects that misuse poses minimal risk—an AI agent could only read announcements it is already authorized to access.
From the tool's definition Tool name 'baseline_get_announcements' and description 'Vendor proactive notifications (e.g. scheduled server-maintenance banners), as plain text' indicate a retrieval operation. The server is explicitly described as 'read-only interaction'.
Attacks that exploit this kind of access
Vendor proactive notifications (e.g. scheduled server-maintenance banners), as plain text. It is categorised as a Read tool in the Baseline MCP Server, which means it retrieves data without modifying state.
Register the Baseline MCP server in PolicyLayer and add a rule for baseline_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 Baseline. Nothing to install.
baseline_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 baseline_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 baseline_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.
baseline_get_announcements is provided by the Baseline MCP server (swannman/baseline-irrigation-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 →