Viam · Capability

Viam Vision Service — Detections

Run object detection against camera images.

Viam Vision Service — Detections 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: Detect objects from camera. Can be deployed as a REST endpoint, MCP tool, or Agent Skill via Naftiko.

Tagged areas include Viam, Vision, and Detections.

Run with Naftiko ViamVisionDetections

MCP Tools

viam-detect-from-camera

Detect objects from camera.

read-only idempotent
viam-detect-from-image

Detect objects in image.

read-only idempotent
viam-object-point-clouds

3D segment objects.

read-only idempotent

Capability Spec

vision-detections.yaml Raw ↑
naftiko: 1.0.0-alpha2
info:
  label: Viam Vision Service — Detections
  description: Run object detection against camera images.
  tags: [Viam, Vision, Detections]
  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-detections
    baseUri: '{{env.VIAM_MACHINE_ADDRESS}}'
    description: Viam VisionService.
    resources:
    - name: get-detections-from-camera
      path: /viam.service.vision.v1.VisionService/GetDetectionsFromCamera
      operations:
      - { name: getDetectionsFromCamera, method: POST, description: Detect objects in a camera frame., outputRawFormat: json, inputParameters: [{ name: body, in: body, type: object, required: true }] }
    - name: get-detections
      path: /viam.service.vision.v1.VisionService/GetDetections
      operations:
      - { name: getDetections, method: POST, description: Detect objects in a provided image., outputRawFormat: json, inputParameters: [{ name: body, in: body, type: object, required: true }] }
    - name: get-object-point-clouds
      path: /viam.service.vision.v1.VisionService/GetObjectPointClouds
      operations:
      - { name: getObjectPointClouds, method: POST, description: 3D segment objects from a camera., 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-detections-mcp
    port: 9090
    transport: http
    description: MCP adapter for object detection.
    tools:
    - { name: viam-detect-from-camera, description: Detect objects from camera., hints: { readOnly: true, destructive: false, idempotent: true }, call: vision-detections.getDetectionsFromCamera, with: { body: tools.body } }
    - { name: viam-detect-from-image, description: Detect objects in image., hints: { readOnly: true, destructive: false, idempotent: true }, call: vision-detections.getDetections, with: { body: tools.body } }
    - { name: viam-object-point-clouds, description: 3D segment objects., hints: { readOnly: true, destructive: false, idempotent: true }, call: vision-detections.getObjectPointClouds, with: { body: tools.body } }