Sleeek MCP Server - Production Ready
LocalAbout Sleeek MCP Server - Production Ready
SleeekApp's MCP server assesses photos with context carried across attempts. It tracks camera-angle changes and constraints to provide progressive feedback for photo assessment.
Key features
- 01Retains context across assessments
- 02Avoids repeating prior feedback
- 03Tracks physical constraints
- 04Detects camera-angle changes
- 05Progressive feedback across up to three attempts
Use cases
- 01Assess successive photo attempts with prior context
- 02Request a fresh assessment after changing camera angle
MCP support
The MCP server exposes photo assessment for SleeekApp through the `/assess` endpoint, returning feedback, attempt number, angle-reset status, score, acceptability, and constraints.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESleeek MCP Server - Production Ready
This MCP server provides context-aware photo assessment for SleeekApp with:
- ✅ Context memory across attempts
- ✅ Angle change detection
- ✅ Constraint learning
- ✅ Progressive feedback
- ✅ Future agentic capabilities
Quick Deploy to Railway
1. Push to GitHub
cd ~/Desktop/sleeek-mcp-deploy
git init
git add .
git commit -m "Initial MCP server"
git branch -M main
git remote add origin YOUR_GITHUB_REPO_URL
git push -u origin main
2. Deploy to Railway
- Go to railway.app
- Click "New Project" → "Deploy from GitHub repo"
- Select your repo
- Add environment variable:
OPENAI_API_KEY - Deploy!
Railway will give you a URL like: https://sleeek-mcp.up.railway.app
3. Update Your iOS App
In MCPClient.swift, change:
private let bridgeURL = "https://sleeek-mcp.up.railway.app"
Local Development
npm install
cp .env.example .env
# Add your OpenAI API key to .env
npm start
Features
Context Awareness
- Remembers previous assessments
- Won't repeat the same feedback
- Tracks physical constraints
- Progressive acceptance (3 attempts max)
Angle Detection
- Detects >30° camera movement
- Resets context for new angles
- Fresh assessment from new position
Future Agentic Capabilities
This MCP architecture enables:
- Multi-step planning
- Cross-room optimization
- Learning from all users
- Personalized style adaptation
- Integration with other tools
API Endpoints
POST /assess
{
"imageBase64": "...",
"roomType": "living",
"shootId": "uuid",
"currentAngle": {
"pitch": 0,
"yaw": 0,
"roll": 90
}
}
Response:
{
"feedback": "Move left to include the fireplace. The sofa is well-framed.",
"attemptNumber": 1,
"angleReset": false,
"score": 75,
"isAcceptable": false,
"constraints": []
}
Production Considerations
- Database: Replace in-memory storage with PostgreSQL
- Authentication: Add API keys for security
- Rate Limiting: Prevent abuse
- Monitoring: Add logging service
- Caching: Cache similar assessments
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.