DINO-X Image Detection MCP Server

Instructions

Implementation Reference

• src/servers/http-server.ts:230-306 (handler)

  MCP tool handler implementation for 'detect-human-pose-keypoints' in HTTP server. Includes inline input schema (Zod), API client call, bbox and pose keypoints parsing, categorization, and formatted text response.
  private registerDetectHumanPoseKeypointsTool(): void { const { name, description } = ToolConfigs[Tool.DETECT_HUMAN_POSE_KEYPOINTS]; this.server.tool( name, description, { imageFileUri: z.string().describe("URI of the input image. Preferred for remote or local files. Must start with 'https://'."), includeDescription: z.boolean().describe("Whether to return a description of the objects detected in the image, but will take longer to process."), }, async (args) => { try { const { imageFileUri, includeDescription } = args; if (!imageFileUri) { return { content: [ { type: 'text', text: 'Image file URI is required', }, ], } } const { objects } = await this.api.detectHumanPoseKeypoints(imageFileUri, includeDescription); const categories: ResultCategory = {}; for (const object of objects) { if (!categories[object.category]) { categories[object.category] = []; } categories[object.category].push(object); } const objectsInfo = objects.map(obj => { const bbox = parseBbox(obj.bbox); const pose = obj.pose ? parsePoseKeypoints(obj.pose) : undefined; return { name: obj.category, bbox, pose, ...(includeDescription ? { description: obj.caption, } : {}), } }); return { content: [ { type: "text", text: `${objectsInfo.length} human(s) detected in image.` }, { type: "text", text: `Detailed human pose keypoints detection results: ${JSON.stringify((objectsInfo), null, 2)}` }, { type: "text", text: `Note: The bbox coordinates are in {xmin, ymin, xmax, ymax} format, where the origin (0,0) is at the top-left corner of the image. The pose keypoints follow the same coordinate system, with visibility states (not visible, visible).` }, ] }; } catch (error) { return { content: [ { type: 'text', text: `Failed to detect human pose keypoints from image: ${error instanceof Error ? error.message : String(error)}`, }, ], }; } } ) }
• src/servers/stdio-server.ts:197-273 (handler)

  MCP tool handler implementation for 'detect-human-pose-keypoints' in STDIO server. Includes inline input schema (Zod), API client call, bbox and pose keypoints parsing, categorization, and formatted text response.
  private registerDetectHumanPoseKeypointsTool(): void { const { name, description } = ToolConfigs[Tool.DETECT_HUMAN_POSE_KEYPOINTS]; this.server.tool( name, description, { imageFileUri: z.string().describe("URI of the input image. Preferred for remote or local files. Must start with 'https://' or 'file://'."), includeDescription: z.boolean().describe("Whether to return a description of the objects detected in the image, but will take longer to process."), }, async (args) => { try { const { imageFileUri, includeDescription } = args; if (!imageFileUri) { return { content: [ { type: 'text', text: 'Image file URI is required', }, ], } } const { objects } = await this.api.detectHumanPoseKeypoints(imageFileUri, includeDescription); const categories: ResultCategory = {}; for (const object of objects) { if (!categories[object.category]) { categories[object.category] = []; } categories[object.category].push(object); } const objectsInfo = objects.map(obj => { const bbox = parseBbox(obj.bbox); const pose = obj.pose ? parsePoseKeypoints(obj.pose) : undefined; return { name: obj.category, bbox, pose, ...(includeDescription ? { description: obj.caption, } : {}), } }); return { content: [ { type: "text", text: `${objectsInfo.length} human(s) detected in image.` }, { type: "text", text: `Detailed human pose keypoints detection results: ${JSON.stringify((objectsInfo), null, 2)}` }, { type: "text", text: `Note: The bbox coordinates are in {xmin, ymin, xmax, ymax} format, where the origin (0,0) is at the top-left corner of the image. The pose keypoints follow the same coordinate system, with visibility states (not visible, visible).` }, ] }; } catch (error) { return { content: [ { type: 'text', text: `Failed to detect human pose keypoints from image: ${error instanceof Error ? error.message : String(error)}`, }, ], }; } } ) }
• src/dino-x/client.ts:219-233 (helper)

  Core DinoXApiClient method implementing the detection logic specific to human pose keypoints by setting 'person' text prompt and including 'pose_keypoints' in targets, delegating to performDetection which handles API task creation and polling.
  async detectHumanPoseKeypoints( imageFileUri: string, includeDescription: boolean ): Promise<DetectionResult> { return this.performDetection(imageFileUri, includeDescription, { model: "DINO-X-1.0", prompt: { type: "text", text: "person" }, targets: ["bbox", "pose_keypoints"], bbox_threshold: 0.25, iou_threshold: 0.8 }); }
• src/utils/index.ts:55-80 (helper)

  Utility function to parse raw API pose keypoints array into structured object mapping 17 standard keypoints to {x, y, visible}.
  export const parsePoseKeypoints = (pose: number[]) => { const keypointNames = [ 'nose', 'leftEye', 'rightEye', 'leftEar', 'rightEar', 'leftShoulder', 'rightShoulder', 'leftElbow', 'rightElbow', 'leftWrist', 'rightWrist', 'leftHip', 'rightHip', 'leftKnee', 'rightKnee', 'leftAnkle', 'rightAnkle' ]; const structuredPose: { [key: string]: { x: number; y: number; visible: string; } } = {}; for (let i = 0; i < keypointNames.length; i++) { const baseIndex = i * 4; const visibilityMap = { 0: 'not visible', 2: 'visible' }; structuredPose[keypointNames[i]] = { x: parseFloat(pose[baseIndex].toFixed(1)), y: parseFloat(pose[baseIndex + 1].toFixed(1)), visible: visibilityMap[pose[baseIndex + 2] as keyof typeof visibilityMap], }; } return structuredPose; };
• src/constants/tool.ts:24-27 (schema)

  Tool configuration defining the name and description used for MCP registration.
  [Tool.DETECT_HUMAN_POSE_KEYPOINTS]: { name: Tool.DETECT_HUMAN_POSE_KEYPOINTS, description: "Detects 17 keypoints for each person in an image, supporting body posture and movement analysis.", },