Viam · Capability

Viam Vision Service — Classifications

Run image classification against camera images.

Viam Vision Service — Classifications is a Naftiko capability published by Viam, one of 27 capabilities the APIs.io network indexes for this provider. It bundles 3 operations.

The capability includes 3 read-only operations. Lead operation: Classify camera frame. Can be deployed as a REST endpoint, MCP tool, or Agent Skill via Naftiko.

Tagged areas include Viam, Vision, and Classifications.

Run with Naftiko ViamVisionClassifications

MCP Tools

viam-classify-from-camera

Classify camera frame.

read-only idempotent
viam-classify-image

Classify image.

read-only idempotent
viam-capture-all-from-camera

One-shot vision capture.

read-only idempotent

Capability Spec

vision-classifications.yaml Raw ↑ 
naftiko: 1.0.0-alpha2
info:
  label: Viam Vision Service — Classifications
  description: Run image classification against camera images.
  tags: [Viam, Vision, Classifications]
  created: '2026-05-25'
  modified: '2026-05-25'
binds:
- namespace: env
  keys:
    VIAM_API_KEY: VIAM_API_KEY
    VIAM_MACHINE_ADDRESS: VIAM_MACHINE_ADDRESS
capability:
  consumes:
  - type: http
    namespace: vision-classifications
    baseUri: '{{env.VIAM_MACHINE_ADDRESS}}'
    description: Viam VisionService.
    resources:
    - name: get-classifications-from-camera
      path: /viam.service.vision.v1.VisionService/GetClassificationsFromCamera
      operations:
      - { name: getClassificationsFromCamera, method: POST, description: Classify a camera frame., outputRawFormat: json, inputParameters: [{ name: body, in: body, type: object, required: true }] }
    - name: get-classifications
      path: /viam.service.vision.v1.VisionService/GetClassifications
      operations:
      - { name: getClassifications, method: POST, description: Classify a provided image., outputRawFormat: json, inputParameters: [{ name: body, in: body, type: object, required: true }] }
    - name: capture-all-from-camera
      path: /viam.service.vision.v1.VisionService/CaptureAllFromCamera
      operations:
      - { name: captureAllFromCamera, method: POST, description: One-shot vision capture., 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: vision-classifications-mcp
    port: 9090
    transport: http
    description: MCP adapter for image classification.
    tools:
    - { name: viam-classify-from-camera, description: Classify camera frame., hints: { readOnly: true, destructive: false, idempotent: true }, call: vision-classifications.getClassificationsFromCamera, with: { body: tools.body } }
    - { name: viam-classify-image, description: Classify image., hints: { readOnly: true, destructive: false, idempotent: true }, call: vision-classifications.getClassifications, with: { body: tools.body } }
    - { name: viam-capture-all-from-camera, description: One-shot vision capture., hints: { readOnly: true, destructive: false, idempotent: true }, call: vision-classifications.captureAllFromCamera, with: { body: tools.body } }