mcpctl/docs/virtual-llms.md

Virtual LLMs

A virtual LLM is an Llm row in mcpd that's registered by an mcplocal client rather than created by hand with mcpctl create llm. Inference for a virtual LLM is relayed back through the publishing mcplocal's SSE control channel — mcpd never needs to know the local URL or hold its API key.

When the publishing mcplocal goes away (or the user shuts down their laptop) the row decays: active → inactive after 90 s without a heartbeat, then deleted after 4 h of inactivity. A reconnecting mcplocal adopts the same row using a sticky providerSessionId it persisted at first publish.

When to use this

• Local model on a developer laptop that you want everyone on the team to be able to chat with via mcpctl chat-llm <name>. The model doesn't need to be reachable from mcpd's k8s pods — only the user's mcplocal does (which is already the case because mcplocal pulls projects from mcpd over HTTPS).
• Hibernating models that wake on demand (v2 — see "Roadmap").
• Pool of identical models distributed across user laptops, eligible for load balancing (v4).

If your model is reachable from mcpd's k8s pods over LAN/VPN, you don't need a virtual LLM — just mcpctl create llm <name> --type openai --url … and you're done.

Publishing a local provider

mcplocal's local config (~/.mcpctl/config.json) gains a publish: true opt-in per provider:

{
  "llm": {
    "providers": [
      {
        "name": "vllm-local",
        "type": "openai",
        "model": "Qwen/Qwen2.5-7B-Instruct-AWQ",
        "url": "http://127.0.0.1:8000/v1",
        "tier": "fast",
        "publish": true
      }
    ]
  }
}

Restart mcplocal:

systemctl --user restart mcplocal

The registrar:

1. Reads ~/.mcpctl/credentials for mcpdUrl + bearer token.
2. POSTs to /api/v1/llms/_provider-register with the publishable set.
3. Persists the returned providerSessionId to ~/.mcpctl/provider-session so the next restart adopts the same mcpd row.
4. Opens the SSE channel at /api/v1/llms/_provider-stream.
5. Heartbeats every 30 s.
6. Listens for event: task frames and runs them against the local LlmProvider.

If ~/.mcpctl/credentials doesn't exist (e.g. you haven't run mcpctl auth login), the registrar logs a warning and skips — publishing is a best-effort feature, not a boot blocker.

Verifying

$ mcpctl get llm
NAME             KIND     STATUS    TYPE     MODEL                          TIER  KEY                                 ID
qwen3-thinking   public   active    openai   qwen3-thinking                 fast  secret://litellm-key/API_KEY        cmofx8y7u…
vllm-local       virtual  active    openai   Qwen/Qwen2.5-7B-Instruct-AWQ   fast  -                                   cmoxz12ab…

$ mcpctl chat-llm vllm-local
─────────────────────────────────────────────────────────
LLM: vllm-local  openai → Qwen/Qwen2.5-7B-Instruct-AWQ
Kind: virtual    Status: active
─────────────────────────────────────────────────────────
> hello?
Hi! …

You can also chat with public LLMs the same way:

$ mcpctl chat-llm qwen3-thinking

The CLI doesn't care about kind — mcpd's /api/v1/llms/<name>/infer route branches on it server-side.

Lifecycle in detail

State	What it means
active	Heartbeat received within the last 90 s and the SSE channel is open.
inactive	Either the SSE closed or the heartbeat watchdog tripped. Inference returns 503.
hibernating	Publisher is online but the backend is asleep; the next inference triggers a wake task before relaying.

Two timers on mcpd run the GC sweep:

• 90 s without a heartbeat → flip active → inactive.
• 4 h in inactive → delete the row entirely.

A reconnecting mcplocal with the same providerSessionId revives every inactive row it owns; it only orphans rows that fell past the 4-h cutoff.

Inference relay

When mcpd receives POST /api/v1/llms/<virtual>/infer:

1. Look up the row, see kind=virtual + status=active.
2. Find the open SSE session for that providerSessionId. Missing session → 503.
3. Push a { kind: "infer", taskId, llmName, request, streaming } task frame onto the SSE.
4. mcplocal pulls, calls LlmProvider.complete(...), and POSTs the result back to /api/v1/llms/_provider-task/<taskId>/result:
   • non-streaming: { status: 200, body: <chat.completion> }
   • streaming: per-chunk { chunk: { data, done? } }
   • failure: { error: "..." }
5. mcpd forwards the result/chunks out to the original caller.

v1 caveat — streaming granularity: LlmProvider.complete() returns a finalized CompletionResult, not a token stream. Streaming requests therefore arrive at the caller as a single delta + [DONE]. Real per-token streaming is a v2 concern.

Wake-on-demand (v2)

A provider whose backend hibernates (a vLLM instance that suspends when idle, an Ollama daemon that exits when nothing's connected, …) can declare a wake recipe in mcplocal config. When that provider's isAvailable() returns false at registrar startup, the row is published as status=hibernating. The next inference request that hits the row triggers the recipe and waits for the backend to come up before relaying.

Two recipe types:

// HTTP — POST to a "wake controller" that starts the backend out of band.
{
  "name": "vllm-local",
  "type": "openai",
  "model": "...",
  "publish": true,
  "wake": {
    "type": "http",
    "url": "http://10.0.0.50:9090/wake/vllm",
    "method": "POST",
    "headers": { "Authorization": "Bearer ..." },
    "maxWaitSeconds": 60
  }
}

// command — spawn a local process (systemd, wakeonlan, custom script).
{
  "name": "vllm-local",
  "type": "openai",
  "model": "...",
  "publish": true,
  "wake": {
    "type": "command",
    "command": "/usr/local/bin/start-vllm",
    "args": ["--profile", "qwen3"],
    "maxWaitSeconds": 120
  }
}

How a request flows when the row is hibernating:

client → mcpd POST /api/v1/llms/<name>/infer
         mcpd: status === hibernating → push wake task on SSE
         mcplocal: receive wake task → run recipe → poll isAvailable()
                   → heartbeat each tick → POST { ok: true } back
         mcpd: flip row → active, push the original infer task
         mcplocal: run inference → POST result back
mcpd → client (forwards the inference result)

Concurrent infers for the same hibernating Llm share a single wake task — only the first request triggers the recipe; later ones await the same in-flight wake promise. After the wake settles, every queued infer dispatches in order.

If the recipe fails (HTTP non-2xx, command exits non-zero, or the provider doesn't come up within maxWaitSeconds), every queued infer is rejected with a clear error and the row stays hibernating — the next request gets a fresh wake attempt.

Roadmap (later stages)

• v3 — Virtual agents: mcplocal publishes its local agent configs (model + system prompt + sampling defaults) into mcpd's Agent table.
• v4 — LB pool by model: agents can target a model name instead of a specific Llm; mcpd picks the healthiest pool member per request.
• v5 — Task queue: persisted requests for hibernating/saturated pools. Workers pull tasks of their model when they come online.

API surface (v1)

POST  /api/v1/llms/_provider-register      → returns { providerSessionId, llms[] }
GET   /api/v1/llms/_provider-stream        → SSE channel; require x-mcpctl-provider-session header
POST  /api/v1/llms/_provider-heartbeat     → { providerSessionId }
POST  /api/v1/llms/_provider-task/:id/result
                                           → one of:
                                             { error: "msg" }
                                             { chunk: { data, done? } }
                                             { status, body }

GET   /api/v1/llms                         → list (now includes kind, status, lastHeartbeatAt, inactiveSince)
POST  /api/v1/llms/<virtual>/infer         → routes through the SSE relay
DELETE /api/v1/llms/<virtual>              → delete unconditionally (also runs GC's job)

RBAC piggybacks on view/edit/create:llms — no new resource. Publishing a virtual LLM is morally a create:llms operation.

See also

• agents.md — what an Agent is and how it pins to an LLM.
• chat.md — mcpctl chat <agent> (full agent flow).
• The CLI: mcpctl chat-llm <name> (this doc) is the stateless counterpart for raw LLM chat.