Triton Inference Server · Capability

Triton Inference Server NVIDIA Triton Inference Server HTTP/REST API — Statistics

Triton Inference Server NVIDIA Triton Inference Server HTTP/REST API — Statistics. 3 operations. Lead operation: Triton Inference Server Get Statistics for All Models. Self-contained Naftiko capability covering one Triton business surface.

Run with Naftiko TritonStatistics

What You Can Do

GET
Allmodelstatistics — Triton Inference Server Get Statistics for All Models
/v1/v2/models/stats
GET
Modelstatistics — Triton Inference Server Get Model Inference Statistics
/v1/v2/models/{model-name}/stats
GET
Modelversionstatistics — Triton Inference Server Get Model Version Inference Statistics
/v1/v2/models/{model-name}/versions/{model-version}/stats

MCP Tools

triton-inference-server-get-statistics

Triton Inference Server Get Statistics for All Models

read-only idempotent
triton-inference-server-get-model

Triton Inference Server Get Model Inference Statistics

read-only idempotent
triton-inference-server-get-model-2

Triton Inference Server Get Model Version Inference Statistics

read-only idempotent

Capability Spec

http-rest-statistics.yaml Raw ↑
naftiko: 1.0.0-alpha2
info:
  label: Triton Inference Server NVIDIA Triton Inference Server HTTP/REST API — Statistics
  description: 'Triton Inference Server NVIDIA Triton Inference Server HTTP/REST API — Statistics. 3 operations. Lead operation:
    Triton Inference Server Get Statistics for All Models. Self-contained Naftiko capability covering one Triton business
    surface.'
  tags:
  - Triton
  - Statistics
  created: '2026-05-19'
  modified: '2026-05-19'
binds:
- namespace: env
  keys:
    TRITON_API_KEY: TRITON_API_KEY
capability:
  consumes:
  - type: http
    namespace: http-rest-statistics
    baseUri: http://localhost:8000
    description: Triton Inference Server NVIDIA Triton Inference Server HTTP/REST API — Statistics business capability. Self-contained,
      no shared references.
    resources:
    - name: v2-models-stats
      path: /v2/models/stats
      operations:
      - name: allmodelstatistics
        method: GET
        description: Triton Inference Server Get Statistics for All Models
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
    - name: v2-models-model_name-stats
      path: /v2/models/{model_name}/stats
      operations:
      - name: modelstatistics
        method: GET
        description: Triton Inference Server Get Model Inference Statistics
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
    - name: v2-models-model_name-versions-model_version-stats
      path: /v2/models/{model_name}/versions/{model_version}/stats
      operations:
      - name: modelversionstatistics
        method: GET
        description: Triton Inference Server Get Model Version Inference Statistics
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
  exposes:
  - type: rest
    namespace: http-rest-statistics-rest
    port: 8080
    description: REST adapter for Triton Inference Server NVIDIA Triton Inference Server HTTP/REST API — Statistics. One Spectral-compliant
      resource per consumed operation, prefixed with /v1.
    resources:
    - path: /v1/v2/models/stats
      name: v2-models-stats
      description: REST surface for v2-models-stats.
      operations:
      - method: GET
        name: allmodelstatistics
        description: Triton Inference Server Get Statistics for All Models
        call: http-rest-statistics.allmodelstatistics
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/v2/models/{model-name}/stats
      name: v2-models-model-name-stats
      description: REST surface for v2-models-model_name-stats.
      operations:
      - method: GET
        name: modelstatistics
        description: Triton Inference Server Get Model Inference Statistics
        call: http-rest-statistics.modelstatistics
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/v2/models/{model-name}/versions/{model-version}/stats
      name: v2-models-model-name-versions-model-version-stats
      description: REST surface for v2-models-model_name-versions-model_version-stats.
      operations:
      - method: GET
        name: modelversionstatistics
        description: Triton Inference Server Get Model Version Inference Statistics
        call: http-rest-statistics.modelversionstatistics
        outputParameters:
        - type: object
          mapping: $.
  - type: mcp
    namespace: http-rest-statistics-mcp
    port: 9090
    transport: http
    description: MCP adapter for Triton Inference Server NVIDIA Triton Inference Server HTTP/REST API — Statistics. One tool
      per consumed operation, routed inline through this capability's consumes block.
    tools:
    - name: triton-inference-server-get-statistics
      description: Triton Inference Server Get Statistics for All Models
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: http-rest-statistics.allmodelstatistics
      outputParameters:
      - type: object
        mapping: $.
    - name: triton-inference-server-get-model
      description: Triton Inference Server Get Model Inference Statistics
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: http-rest-statistics.modelstatistics
      outputParameters:
      - type: object
        mapping: $.
    - name: triton-inference-server-get-model-2
      description: Triton Inference Server Get Model Version Inference Statistics
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: http-rest-statistics.modelversionstatistics
      outputParameters:
      - type: object
        mapping: $.