AI agents call get_consumption_report to retrieve information from Md24de without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to retrieve historical consumption data or reports based on context from the messdienst24.de utility portal integration and sibling tools. Retrieving consumption reports is a read-only operation with no data modification, deletion, or side effects. The empty description prevents higher confidence, but the functional context strongly suggests read access to existing reports/data.
From the tool's definition Tool name 'get_consumption_report' paired with sibling tools 'get_last_available_month' and 'save_pdf' and server description mentioning 'retrieve heating and hot-water consumption data' and 'download PDF reports' indicate data retrieval.
Attacks that exploit this kind of access
get_consumption_report. It is categorised as a Read tool in the Md24de MCP Server, which means it retrieves data without modifying state.
Register the Md24de MCP server in PolicyLayer and add a rule for get_consumption_report: 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 Md24de. Nothing to install.
get_consumption_report 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_consumption_report 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_consumption_report. 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_consumption_report is provided by the Md24de MCP server (volsch/md24de-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 →