the-real-hetzner-mcp
by mguttmann
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | debug, info, warn or error. Logs are JSON on stderr; stdout carries the MCP protocol. Default: warn | |
| HTTP_TIMEOUT_MS | No | Wall-clock budget for one API request, all attempts and retry delays included. Default: 30000 | |
| HETZNER_API_BASE | No | API base URL. Must be https; plain http only for localhost, 127.0.0.1 or ::1. Any other value stops the server at startup. Default: https://api.hetzner.cloud/v1 | |
| MAX_OUTPUT_BYTES | No | Largest tool result text in bytes, counted as sent (JSON-escaped). A longer result is cut and ends with [output truncated by MAX_OUTPUT_BYTES=...]. Values above the default are lowered to it. Default: 8388608 | |
| HETZNER_API_TOKEN | Yes | Hetzner Cloud API token, sent as a bearer token on every request. Required. The server can do exactly what this token allows. | |
| HETZNER_READ_ONLY | No | true, 1 or yes: every tool that is not annotated read-only, and hcloud_raw_request with a method other than GET, returns isError without sending a request. Any value other than true, 1, yes, false, 0, no or empty stops the server at startup. Default: false | |
| HETZNER_DENY_TOOLS | No | Comma-separated tool name globs (* any characters, ? one character, whole name, case-sensitive), for example hcloud_delete_*,hcloud_raw_request. A matching tool returns isError without sending a request. A pattern that matches no tool stops the server at startup. Default: empty | |
| PAGINATION_MAX_ITEMS | No | Soft cap on the items an auto-paginated list collects; a capped list reports truncated: true. Default: 500 | |
| PAGINATION_MAX_PAGES | No | Soft cap on the pages an auto-paginated list requests. Default: 10 | |
| PAGINATION_TIMEOUT_MS | No | Wall-clock budget of one auto-paginated list. When it ends, the pages read so far come back with truncated: true and a note. Default: 45000 | |
| ACTION_POLL_TIMEOUT_MS | No | Wall-clock budget of a wait: true call, measured from the start of the call. Also the ceiling for the timeout_ms argument of hcloud_wait_action. Default: 45000 | |
| HETZNER_CONFIRM_WRITES | No | true, 1 or yes: every tool that is not read-only returns a preview unless the call carries confirm: "YES". Default: false | |
| ACTION_POLL_INTERVAL_MS | No | Pause between two polls. The interval_ms argument of hcloud_wait_action cannot go below 1000 or this value, whichever is lower. Default: 2000 | |
| HTTP_MAX_RETRY_DELAY_MS | No | Longest single retry delay. A 429 whose Retry-After asks for more is returned at once as an error. Default: 10000 | |
| MCP_SERVE_MODERN_PROTOCOL | No | true, 1 or yes: also serve the MCP 2026-07-28 revision over stdio. A client that opens with initialize gets the same 2025-era session as with false. Default: false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues