1. System Requirements

2. Building the Server

The server build process installs system dependencies, builds OpenCV from source with DNN support, and compiles the Inigami server binary. The initial setup takes 30-60 minutes due to the OpenCV build; subsequent builds are fast.

3. Building the GUI Client

The Qt 5.12 QML desktop application provides a graphical interface with image gallery, bounding box overlay, and real-time processing feedback. The GUI is optional -- you can use the server with any TCP client.

4. Running Inigami

Start the server and optionally launch the GUI client. The top-level Makefile provides convenience targets for managing both components.

5. Your First Request

With the server running, send a test request using any TCP client. Here is an example using Python:

1import socket
2import json
3
4# Connect to the Inigami server
5sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
6sock.connect(("localhost", 10210))
7
8# Send an object detection request
9request = {
10    "request_id": "test-001",
11    "type": "detect_objects",
12    "image_path": "/path/to/your/image.jpg"
13}
14sock.sendall(json.dumps(request).encode() + b"\n")
15
16# Read the response
17response = json.loads(sock.recv(65536).decode())
18print(json.dumps(response, indent=2))
19
20sock.close()

You should receive a JSON response containing detected objects with class labels, confidence scores, and bounding box coordinates.

6. MCP Tools Setup

To use Inigami as MCP tools with AI assistants like Claude, add the following to your MCP client configuration:

1{
2  "mcpServers": {
3    "inigami": {
4      "command": "inigami-mcp-server",
5      "args": ["--host", "localhost", "--port", "10210"],
6      "env": {}
7    }
8  }
9}

Once configured, AI assistants can invoke Inigami tools for object detection, image processing, text analysis, and more -- all through natural language requests.