Viam · Capability

Viam ML Inference

Run cloud-hosted inference against models registered in the Viam ML registry.

Viam ML Inference is a Naftiko capability published by Viam, one of 27 capabilities the APIs.io network indexes for this provider. It bundles 1 operation.

The capability includes 1 state-changing operation. Lead operation: Run cloud-hosted inference. Can be deployed as a REST endpoint, MCP tool, or Agent Skill via Naftiko.

Tagged areas include Viam, MachineLearning, and Inference.

Run with Naftiko ViamMachineLearningInference

MCP Tools

viam-get-inference

Run cloud-hosted inference.

idempotent

Capability Spec

ml-inference.yaml Raw ↑ 
naftiko: 1.0.0-alpha2
info:
  label: Viam ML Inference
  description: Run cloud-hosted inference against models registered in the Viam ML registry.
  tags: [Viam, MachineLearning, Inference]
  created: '2026-05-25'
  modified: '2026-05-25'
binds:
- namespace: env
  keys:
    VIAM_API_KEY: VIAM_API_KEY
capability:
  consumes:
  - type: http
    namespace: ml-inference
    baseUri: https://app.viam.com
    description: Viam MLInferenceService.
    resources:
    - name: get-inference
      path: /viam.app.mlinference.v1.MLInferenceService/GetInference
      operations:
      - { name: getInference, method: POST, description: Run inference against a registry model., outputRawFormat: json, inputParameters: [{ name: body, in: body, type: object, required: true }] }
    authentication:
      type: apikey
      key: key
      value: '{{env.VIAM_API_KEY}}'
      placement: header
  exposes:
  - type: mcp
    namespace: ml-inference-mcp
    port: 9090
    transport: http
    description: MCP adapter for cloud inference.
    tools:
    - { name: viam-get-inference, description: Run cloud-hosted inference., hints: { readOnly: false, destructive: false, idempotent: true }, call: ml-inference.getInference, with: { body: tools.body } }