{
  "markdown": "# MCP-YOLO\n[![PyPI](https://img.shields.io/pypi/v/mcp-yolo)](https://pypi.org/project/mcp-yolo/)\n[![Downloads](https://static.pepy.tech/personalized-badge/mcp-yolo?period=total&units=international_system&left_color=black&right_color=orange&left_text=Downloads)](https://pepy.tech/project/mcp-yolo)\nmcp-name: io.github.rjn32s/mcp-yolo\n\nMCP-YOLO is an agent-first development platform that provides **Zero-Shot Object Detection and Segmentation** as a Model Context Protocol (MCP) server. Powered by **Ultralytics YOLOE**, it enables developers and AI agents to detect and segment objects using arbitrary text prompts without retraining.\n\n## Key Features\n- **Zero-Shot Detection:** Detect any object using natural language (e.g., \"the blue coffee cup next to the spoon\").\n- **Instance Segmentation:** Precise polygon masks for discovered objects.\n- **Flexible Image Inputs:** Supports local file paths, remote URLs, and Base64 encoded strings.\n- **Agent Optimized:** Includes custom \"Skills\" for autonomous deployment and benchmarking.\n\n## YOLOE Performance Reference\n\nYOLOE builds upon the latest YOLO architectures (like YOLO11 and YOLO26) to provide state-of-the-art open-vocabulary performance.\n\n| Model | Based On | mAP (COCO) | Speed (T4/ms) | Params (M) |\n| :--- | :--- | :---: | :---: | :---: |\n| **YOLOE26-N** | YOLO26-N | 40.9 | 1.7 | ~3.0 |\n| **YOLOE26-S** | YOLO26-S | 48.6 | 2.5 | ~10.0 |\n| **YOLOE26-L** | YOLO26-L | 55.0 | 6.2 | ~40.0 |\n| **YOLOE-L** | YOLO11-L | ~52.0 | ~5.0 | ~26.0 |\n\n*Note: Performance varies depending on the hardware and input resolution. `mcp-yolo` uses `yoloe-26l-seg.pt` by default for high precision.*\n\n## Quick Start\n\n### Installation\n```bash\nuv pip install mcp-yolo\n```\n\n### Running the Server\n```bash\nuv run mcp-yolo\n```\n\n##  MCP Tools\n\n### `detect_objects`\nPerforms zero-shot detection.\n- **Arguments:**\n  - `image_source` (str): Path, URL, or Base64.\n  - `classes` (list[str], optional): Custom text prompts to detect.\n\n### `segment_objects`\nPerforms zero-shot instance segmentation.\n- **Arguments:**\n  - `image_source` (str): Path, URL, or Base64.\n  - `classes` (list[str], optional): Custom text prompts to segment.\n\n##  Publishing\nThis project is configured for automated PyPI publishing. See the [pypi_setup_guide.md](file:///Users/rajanshukla/.gemini/antigravity/brain/6a2d32ac-d625-45bb-8f98-3d2916ab776e/pypi_setup_guide.md) for details.\n",
  "bytes": 2390,
  "sha": "54442573f3aea0884a90f3a330a2417f7dbfaec3ce3bdda2ec78a5fec8976f3c",
  "repo_slug": "rjn32s/mcp-yolo",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_rjn32s_mcp_yolo_a03175b5/readme"
}