AI agents call contribute_or_report to retrieve information from Hetzner without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and returns a pre-filled GitHub issue URL and contribution steps. It does not create, modify, execute, or delete anything; it is purely informational output.
From the tool's definition 'this returns a prefilled GitHub issue link and the steps to open a pull request' — the tool only generates/returns informational links and instructions, no side effects
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
When a Hetzner capability is missing or misbehaving, this returns a prefilled GitHub issue link and the steps to open a pull request. Every gap can become a contribution. It is categorised as a Read tool in the Hetzner MCP Server, which means it retrieves data without modifying state.
Register the Hetzner MCP server in PolicyLayer and add a rule for contribute_or_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 Hetzner. Nothing to install.
contribute_or_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 contribute_or_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 contribute_or_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.
contribute_or_report is provided by the Hetzner MCP server (mjmirza/hetzner-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 →