AI-Profile-Router/platform/hermes/skills/mcphub-deployer/SKILL.md

name, description

name	description
mcphub-deployer	Install, update, disable, test, publish, or inspect portable MCP servers in CasaDeRoll MCPHub on Unraid. Use for MCP repositories, packages, binaries, HTTP MCPs, client registration, MCPHub repair, or moving an MCP out of Athena or Hermes.

MCPHub Deployer

Install portable MCPs in the existing MCPHub; never create a separate container and never install them inside Hermes.

Fixed map

• Unraid: 192.168.1.2; container: MCPHub; base URL: http://192.168.1.2:8787
• Appdata: /mnt/nvme-storage/appdata/MCPHub
• Work: /mnt/nvme-storage/appdata/MCPHub/work/<id>
• Extensions: /mnt/nvme-storage/appdata/MCPHub/extensions/<id>
• Registry: /mnt/nvme-storage/appdata/MCPHub/config/mcp-registry.json
• Secret: /mnt/nvme-storage/appdata/MCPHub/secrets/<id>.env (0600)
• Helper in container: /opt/casaderoll/deploy-extension.py
• Route: http://192.168.1.2:8787/mcp/<id>

Do not search for other checkouts, registries, templates, or secret stores. Normal extensions do not modify Dockerfile, image tag, Unraid template, MCPHub source, or Hermes config manually.

Hard credential boundary

Credentials are user input. Check only whether the dedicated secret file and required keys exist; never print values. Never inspect other containers, environments, mail servers, configs, histories, or passwords to find or infer credentials. If credentials are missing, complete credential-independent build work, stage the MCP disabled, report the exact secret path and missing key names, then stop. Never publish or authenticate it.

One-pass workflow

1. Read this skill once. Inspect only MCPHub state, the fixed registry, the dedicated secret-file presence, and the target upstream release/source.
2. Classify once: existing HTTP MCP, packaged stdio MCP, released binary, custom MCP, or host-bound HTTP proxy. Do not reconsider without a concrete failed build or handshake.
3. Interpret intent: “prüfen/planen” changes nothing; “installieren/einbauen” continues; “deaktiviert” never activates; “read-only” omits mutating tools.
4. Build only in /tmp or the fixed work directory. Pin versions and verify checksums. Put runtime files in the work directory, not in the repository.
5. Write one compact manifest at <work>/manifest.json:

{
  "server": {
    "id": "example", "hermes_id": "example", "name": "Example",
    "description": "Short tool-selection description",
    "url": "http://192.168.1.2:8787/mcp/example",
    "clients": ["hermes"],
    "deployment": {"required_env": ["EXAMPLE_TOKEN"]},
    "hub": {
      "type": "stdio", "secret_file": "example.env",
      "command": "/usr/local/bin/run-with-env",
      "args": ["/run/secrets/mcphub/example.env", "--", "node", "/app/data/extensions/example/index.js"],
      "enabled": false
    }
  },
  "artifacts": [
    {"source": "/app/data/work/example/index.js", "path": "index.js", "sha256": "HEX", "mode": "0644"}
  ]
}

Use paths as seen inside MCPHub (/app/data/...) in the manifest. 6. Stage with exactly:

docker exec MCPHub python3 /opt/casaderoll/deploy-extension.py stage \
  --manifest /app/data/work/<id>/manifest.json

The helper copies verified files, updates the registry atomically, and always stages disabled. It technically blocks activation when the dedicated secret or a required key is missing. 7. The helper registers the disabled server through MCPHub's official API. Do not recreate MCPHub and do not restart Hermes, Athena, Router, Qwen, WireGuard, Unraid, or other services. 8. If credentials are ready, activate with the helper, then verify: health; all old routes; new handshake; list_tools schemas; one bounded read-only call; no test writes or residue. Otherwise stop while disabled. 9. Ask Hermes to reload MCP connections. Hermes uses MCPHub's aggregate /mcp endpoint, so no per-server client config or YAML edit is needed. 10. Report version, state, tool count, secret path (never values), tests, client sync, durable source status, and rollback.

Limits

• At most six preflight reads and two attempts per hypothesis.
• At most one corrected build.
• Never dump full registries, repository trees, logs, or configs; use bounded queries and compact JSON.
• Never use one giant shell call to write several files.
• Never claim success without observed handshake and probe results.
• On failure leave the previous MCPHub running and the new extension disabled.
• Ask before destructive actions or credential rotation not explicitly asked.

Resume

Before compression write <work>/checkpoint.json containing only phase, version, completed checks, pending action, modified paths, and rollback. After compression reload this skill and that checkpoint before continuing. Delete the checkpoint only after success.