Compute

compute: 28 operations.

Also for this capability: API · CLI · MCP · SDKs

compute: 28 operations. Name one in "op" and pass that operation's own arguments in "input". describe returns an operation's input schema.

Tool	`compute`
Address	`https://api.hanzo.ai/v1/mcp`
Method	`tools/call` (JSON-RPC 2.0)
Arguments	2, 1 required
Operation	`POST /v1/compute/clusters` · `PUT /v1/compute/machines/{id}/agent` · `POST /v1/compute/fleet/jobs/{id}/cancel` · `POST /v1/compute/k8s/clusters` · `POST /v1/compute/clusters/{clusterId}/pools` · `DELETE /v1/compute/k8s/clusters/{id}` · `DELETE /v1/compute/machines/{id}` · `DELETE /v1/compute/clusters/{clusterId}/pools/{poolId}` · `DELETE /v1/compute/clusters/{id}` · `GET /v1/compute/k8s/clusters/{id}` · `GET /v1/compute/machines/{id}` · `GET /v1/compute/machines/{id}/agent` · `GET /v1/compute/clusters` · `GET /v1/compute/fleet` · `GET /v1/compute/fleet/jobs` · `GET /v1/compute/fleet/samples` · `GET /v1/compute/fleet/workers` · `GET /v1/compute/gpus/alerts` · `GET /v1/compute/gpus` · `GET /v1/compute/k8s/clusters` · `GET /v1/compute/k8s/nodes` · `GET /v1/compute/machines/agents` · `GET /v1/compute/machines` · `POST /v1/compute/fleet/samples` · `POST /v1/compute/clusters/{clusterId}/pools/{poolId}/scale` · `DELETE /v1/compute/machines/{id}/agent`
Product	compute

Arguments

Field	Type	Required	Default	Values	Description
`input`	`object`	—	—	—	arguments for the chosen op
`op`	`string`	yes	—	—	—

tools/list declares a type, a description, which fields are required and an enumerated value set for each field and nothing further, and every column above is MCP's own. This tool takes an operation name and that operation's arguments, so what the document constrains is what goes inside input, field by field, on the operation you name — ask describe for that. A — means MCP does not constrain the field.

Call it

A tools/call carries every argument in one flat object — nothing binds to a path or a query string. This call carries exactly the arguments the operation requires, so it is the smallest one that can run.

curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "compute",
         "arguments": {
           "op": "list_compute_regions"
         }
       }
     }'

Values are the operation's own defaults and enumerated values where it declares them, and a <placeholder> where neither source declares one. tools/list needs no credential; tools/call does — called without one MCP answers HTTP 200 with a JSON-RPC result whose isError is set and whose text says what was missing. How to get a key →

The operation behind it

compute dispatches to 28 operations. 26 of them MCP names exactly as the document ids them, and those are below; for the rest MCP has its own verb, which describe resolves.

Operation	Route	Product	Summary
`attachCluster`	`POST /v1/compute/clusters`	compute	Attaches a BYO cluster to the caller's org — the kubeconfig is validated, KMS-sealed and added to the fleet — and answers 201 with the cluster as it now appears on GET /v1/compute/clusters.
`bindMachineAgent`	`PUT /v1/compute/machines/{id}/agent`	compute	Binds a cloud Agent to one of the caller org's machines: the machine is recorded as running that Agent's @hanzo/bot runtime.
`cancelFleetJob`	`POST /v1/compute/fleet/jobs/{id}/cancel`	compute	Cancels a queued or running render in the caller's org.
`createKubernetesCluster`	`POST /v1/compute/k8s/clusters`	compute	Provisions a DOKS cluster for the caller's org and answers 201.
`createNodePool`	`POST /v1/compute/clusters/{clusterId}/pools`	compute	Adds a node pool to one of the caller org's clusters and answers 201 with the created pool.
`deleteKubernetesCluster`	`DELETE /v1/compute/k8s/clusters/{id}`	compute	Destroys a DOKS cluster by id and answers 204.
`deleteMachine`	`DELETE /v1/compute/machines/{id}`	compute	Terminates one of the caller org's machines.
`deleteNodePool`	`DELETE /v1/compute/clusters/{clusterId}/pools/{poolId}`	compute	Removes a node pool from one of the caller org's clusters.
`detachCluster`	`DELETE /v1/compute/clusters/{id}`	compute	Removes a BYO cluster from the caller org's fleet.
`getKubernetesCluster`	`GET /v1/compute/k8s/clusters/{id}`	compute	Returns one cluster's detail: node pools + worker nodes.
`getMachine`	`GET /v1/compute/machines/{id}`	compute	Returns one of the caller org's machines by its org-scoped name.
`getMachineAgent`	`GET /v1/compute/machines/{id}/agent`	compute	Returns the agent binding of one of the caller org's machines, or 404 when the machine runs no bot runtime.
`listClusters`	`GET /v1/compute/clusters`	compute	Returns the caller org's clusters from both sources: the managed clusters projected from Visor's node pools, and the BYO clusters attached to the caller's project.
`listFleet`	`GET /v1/compute/fleet`	compute	Returns every compute unit the caller's org has, from every source, each carrying its latest utilization: agent run-targets, the BYO machines that dialed in, attached BYO clusters and Visor-provisioned machines.
`listFleetJobs`	`GET /v1/compute/fleet/jobs`	compute	Returns the caller org's gpu-jobs render queue, each row tagged with the GPU it targets (empty = the shared any-GPU lane) and the node claiming it, optionally narrowed to one GPU's queue and/or one status.
`listFleetSamples`	`GET /v1/compute/fleet/samples`	compute	Returns the caller org's utilization series, oldest first.
`listFleetWorkers`	`GET /v1/compute/fleet/workers`	compute	Returns the caller org's BYO machines — the ones that dialed in via `hanzo link` — with everything each host reported about itself.
`listGpuAlerts`	`GET /v1/compute/gpus/alerts`	compute	An HONEST empty surface: Visor exposes no GPU alert inventory, so this returns [] rather than fabricating alerts.
`listGpus`	`GET /v1/compute/gpus`	compute	Returns one row per physical accelerator the caller's org has, derived from its real GPU machines (the size slug says how many cards a node holds) and from the accelerators BYO workers report through nvidia-smi.
`listKubernetesClusters`	`GET /v1/compute/k8s/clusters`	compute	Lists the org's DOKS clusters (Visor, house account) folded with the org's BYO clusters — ONE fleet cluster view under the unified k8s noun.
`listKubernetesNodes`	`GET /v1/compute/k8s/nodes`	compute	Returns every DOKS worker node in the org's clusters as a machine — the SAME set the fleet folds in (managedMachines), exposed directly under the k8s noun.
`listMachineAgents`	`GET /v1/compute/machines/agents`	compute	Returns every agent↔machine binding in the caller's org — which machines are running which cloud Agent, with vm's own reconciled status.
`listMachines`	`GET /v1/compute/machines`	compute	Returns every machine the caller's org has — Visor's registry, the live DigitalOcean droplets and the DOKS worker nodes (deduped into one union), plus the BYO machines that dialed in via `hanzo link` (provider "byo").
`recordFleetSample`	`POST /v1/compute/fleet/samples`	compute	Records a BYO worker's live GPU utilization into the SAME series the fleet board overlays.
`scaleNodePool`	`POST /v1/compute/clusters/{clusterId}/pools/{poolId}/scale`	compute	Resizes a node pool to an absolute node count and returns the pool as Visor reports it after the change.
`unbindMachineAgent`	`DELETE /v1/compute/machines/{id}/agent`	compute	Detaches the agent runtime from one of the caller org's machines.

The same capability over plain HTTP is in the compute API reference, on https://api.hanzo.ai.

All 120 tools · MCP · API reference

Generated from tools/list on https://api.hanzo.ai/v1/mcp — 120 tools captured 2026-09-30.

Was this page useful?

PreviousCompliance NextContent