Headscale MCP connector
by si-essence
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP port. | 3000 |
| HEADSCALE_URL | Yes | Required. Self-hosted Headscale origin, for example http://127.0.0.1:8080. A trailing /api/v1 is stripped. Tailscale hosts are refused. | |
| MCP_TRANSPORT | No | Transport to use: "stdio" or "http". --http overrides. | |
| HEADSCALE_API_KEY | Yes | Headscale API key. Sent as Authorization: Bearer and always redacted in output. | |
| HEADSCALE_CONTACT | No | Contact token in the User-Agent. Must not be the API key. | |
| HEADSCALE_TOOLSETS | No | Comma-separated list of toolsets, or "all". | nodes,users,policy,meta |
| HEADSCALE_PER_MINUTE | No | Local request budget per minute. | 30 |
| HEADSCALE_TIMEOUT_MS | No | Upstream timeout in milliseconds. | 20000 |
| HEADSCALE_ALLOW_WRITES | No | Must be the literal "true" before a confirmed write is sent. Otherwise writes return a dry-run preview and send no write. | false |
| HEADSCALE_CACHE_TTL_SEC | No | GET cache TTL in seconds. Writes clear the cache. | 60 |
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