A Model Context Protocol (MCP) server that delivers zero-shot object detection and segmentation via Ultralytics YOLOE. Built as an agent-first development platform, it exposes detection and segmentation capabilities as MCP-compliant model context for AI agents and tools.

🛠️ Key Features

Zero-shot object detection and segmentation using Ultralytics YOLOE
MCP-compliant server exposing model context for agents
Lightweight readme excerpt indicating project scope and usage
PyPI distribution and download metrics visible in readme

🚀 Use Cases

Integrate zero-shot detection into agent workflows
Enable context-aware decision making with object segmentation outputs
Rapid prototyping of MCP-powered perception modules

⚡ Developer Benefits

Clear MCP server semantics for model context
Easy integration with Ultralytics YOLOE backends
Readme-based guidance and repository activity indicators

⚠️ Limitations

Descriptions are derived from readme excerpt; full feature surface may require external docs
Specific configuration details and API surfaces are not enumerated here

MCP-YOLO

mcp-name: io.github.rjn32s/mcp-yolo

MCP-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.

Key Features

Zero-Shot Detection: Detect any object using natural language (e.g., "the blue coffee cup next to the spoon").

Instance Segmentation: Precise polygon masks for discovered objects.

Flexible Image Inputs: Supports local file paths, remote URLs, and Base64 encoded strings.

Agent Optimized: Includes custom "Skills" for autonomous deployment and benchmarking.

YOLOE Performance Reference

YOLOE builds upon the latest YOLO architectures (like YOLO11 and YOLO26) to provide state-of-the-art open-vocabulary performance.

Model

Based On

mAP (COCO)

Speed (T4/ms)

Params (M)

YOLOE26-N

YOLO26-N

40.9

1.7

~3.0

YOLOE26-S

YOLO26-S

48.6

2.5

~10.0

YOLOE26-L

YOLO26-L

55.0

6.2

~40.0

YOLOE-L

YOLO11-L

~52.0

~5.0

~26.0

Note: Performance varies depending on the hardware and input resolution. mcp-yolo uses yoloe-26l-seg.pt by default for high precision.

MCP Tools

detect_objects

Performs zero-shot detection.

Arguments:

image_source (str): Path, URL, or Base64.
classes (list[str], optional): Custom text prompts to detect.

segment_objects

Performs zero-shot instance segmentation.

Arguments:

image_source (str): Path, URL, or Base64.
classes (list[str], optional): Custom text prompts to segment.

io.github.rjn32s/mcp-yolo

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

MCP-YOLO

Key Features

YOLOE Performance Reference

Quick Start

Installation

Running the Server

MCP Tools

`detect_objects`

`segment_objects`

Publishing

Install

Related servers