Which integrations are available for this server?

Enables cloud-based vision analysis via Google Gemini models, including free tier access. Provides local, private AI vision analysis using Ollama models, enabling image understanding without sending data to external servers. Enables high-quality vision analysis via OpenAI models like GPT-4o.

How do I use OpenSight MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@OpenSight MCP analyze the screenshot on my clipboard" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

OpenSight MCP

by Mr-JoE1

Overview Schema Related Servers Score Discussions

JavaScript

Hybrid

👁️ OpenSight MCP

npm version Node.js License: MIT MCP

Multi-backend AI vision for MCP agents. Analyze images, screenshots, and documents using local Ollama models (private, uncensored) or cloud APIs (OpenAI, Google Gemini, OpenRouter). Works with any MCP-compatible coding agent.

Quick Start

npx opensight-mcp@latest

	Best for	Install
Local & Private	Privacy-first, uncensored, no API keys	`ollama pull minicpm-v:latest`
Free Tier APIs	Zero-cost cloud vision via Google/OpenRouter	Set `GOOGLE_API_KEY` or `OPENROUTER_API_KEY`
Paid APIs	OpenAI GPT-4o, Claude Vision, any OpenAI-compatible	Set `OPENAI_API_KEY`

Related MCP server: pic-id-mcp

🎯 Why OpenSight?

Local & Private	Free Tiers	Multi-Vendor	Agent-Native
Ollama runs on your hardware. No data leaves your network. Uncensored models.	Google Gemini Flash and OpenRouter offer free vision tiers. Zero cost to start.	One tool, any backend. Swap providers with an env var — no code changes.	Purpose-built for MCP agents. Clipboard, file paths, URLs, base64 — all supported.

📦 Installation

Standard config (all MCP clients)

{
  "mcpServers": {
    "opensight": {
      "command": "npx",
      "args": ["opensight-mcp@latest"],
      "env": {
        "OLLAMA_HOST": "127.0.0.1:11434",
        "VISION_MODEL": "minicpm-v:latest"
      }
    }
  }
}

Add to ~/.config/opencode/opencode.jsonc:

{
  "mcp": {
    "opensight": {
      "type": "local",
      "command": ["npx", "opensight-mcp@latest"],
      "enabled": true,
      "env": {
        "OLLAMA_HOST": "192.168.46.34",
        "VISION_MODEL": "minicpm-v:latest"
      }
    }
  }
}

claude mcp add opensight npx opensight-mcp@latest

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "opensight": {
      "command": "npx",
      "args": ["opensight-mcp@latest"],
      "env": {
        "OLLAMA_HOST": "127.0.0.1:11434",
        "VISION_MODEL": "minicpm-v:latest"
      }
    }
  }
}

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "opensight": {
      "command": "npx",
      "args": ["opensight-mcp@latest"]
    }
  }
}

code --add-mcp '{"name":"opensight","command":"npx","args":["opensight-mcp@latest"]}'

Use the standard config above. Same pattern for all MCP-compatible clients.

Add to ~/.hermes/config.yaml:

mcp_servers:
  opensight:
    command: "npx"
    args: ["-y", "opensight-mcp@latest"]
    env:
      OLLAMA_HOST: "127.0.0.1:11434"
      VISION_MODEL: "minicpm-v:latest"

Then reload:

/reload-mcp

Verify it's loaded:

Tell me which MCP-backed tools are available right now.

Manual install (for development)

git clone https://github.com/Mr-JoE1/opensight-mcp.git
cd opensight-mcp
npm install
npm test

🛠️ Tools

vision.analyze_image — General-purpose image analysis. Accepts data URIs (clipboard paste), base64, URLs, or file paths. Configurable system prompt, model, temperature.
vision.describe — UI/QA-focused screenshot analysis. Defaults to a QA system prompt that identifies errors, warnings, and layout issues.
vision.clipboard — Read and analyze images directly from the OS clipboard. Uses clipboardy for cross-platform support (macOS/Windows built-in, Linux needs xclip/wl-clipboard).
vision.find_images — Scan common directories (~/Downloads, ~/Pictures, /tmp) for recently modified images. Zero dependencies — pure Node.js fs.

vision.ocr — Extract text from images using VLM or Tesseract OCR. Supports structured JSON output with text block types.
vision.find_text — Locate specific text in an image with bounding box coordinates. Supports fuzzy matching.

vision.warmup — Pre-load the vision model into GPU VRAM to eliminate cold-start latency.
vision.health — Check backend connection status and list available models.

🔌 Backends

Configure via environment variables. The default is Ollama (local, no API keys needed).

Provider	Env Var	Free Tier	Best For
Ollama	`OLLAMA_HOST`	✅ (your hardware)	Privacy, uncensored, offline
Google Gemini	`GOOGLE_API_KEY`	✅ (Flash 2.0)	Free tier, high accuracy
OpenRouter	`OPENROUTER_API_KEY`	✅ (qwen-vl free)	Multi-model, free tier
OpenAI	`OPENAI_API_KEY`	❌	GPT-4o, best quality

Set the active provider:

# Use Google Gemini (free tier)
export VISION_PROVIDER=google
export GOOGLE_API_KEY=your_key_here

# Use OpenAI (paid)
export VISION_PROVIDER=openai
export OPENAI_API_KEY=sk-...

# Use OpenRouter (free qwen-vl)
export VISION_PROVIDER=openrouter
export OPENROUTER_API_KEY=your_key_here

# Default: Ollama (local)
export OLLAMA_HOST=192.168.46.34:11434

⚙️ Configuration

All settings via environment variables:

Variable	Default	Description
`VISION_ENDPOINT`	`local`	Endpoint mode: `local` (OLLAMA_HOST/PORT) or `global` (OLLAMA_GLOBAL_HOST/PORT)
`OLLAMA_HOST`	`192.168.46.34`	Ollama server host (local endpoint)
`OLLAMA_PORT`	`11434`	Ollama API port (local endpoint)
`OLLAMA_GLOBAL_HOST`	`192.168.46.34`	Ollama server host (global/WAN endpoint)
`OLLAMA_GLOBAL_PORT`	`11434`	Ollama API port (global/WAN endpoint)
`VISION_MODEL`	`minicpm-v:latest`	Default vision model
`OCR_MODEL`	`minicpm-v:latest`	Default OCR model
`VISION_PROVIDER`	`ollama`	Backend: ollama, openai, google, openrouter
`OPENAI_API_KEY`	—	OpenAI API key
`GOOGLE_API_KEY`	—	Google Gemini API key
`OPENROUTER_API_KEY`	—	OpenRouter API key
`MAX_TOKENS`	`2048`	Max response tokens
`VISION_WARMUP_ON_START`	`1`	Auto-warmup model on server start
`VISION_KEEP_ALIVE`	`10m`	Model keep-alive duration
`VISION_TIMEOUT_MS`	`120000`	Request timeout (ms)
`VISION_MAX_RETRIES`	`3`	Retry attempts on failure

Local vs Global Endpoints

Toggle between LAN and WAN endpoints with VISION_ENDPOINT:

Local (default):

export VISION_ENDPOINT=local
export OLLAMA_HOST=192.168.46.34
export OLLAMA_PORT=11434

Global (DDNS/WAN):

export VISION_ENDPOINT=global
export OLLAMA_GLOBAL_HOST=ih-tatweer.duckdns.org
export OLLAMA_GLOBAL_PORT=13313

OpenCode example with both endpoints configured:

{
  "mcp": {
    "vision": {
      "type": "local",
      "command": ["node", "/path/to/vision-mcp.mjs"],
      "env": {
        "VISION_ENDPOINT": "local",
        "OLLAMA_HOST": "192.168.46.34",
        "OLLAMA_PORT": "11434",
        "OLLAMA_GLOBAL_HOST": "ih-tatweer.duckdns.org",
        "OLLAMA_GLOBAL_PORT": "13313",
        "VISION_MODEL": "minicpm-v:latest"
      }
    }
  }
}

🏃 CLI Usage

# Health check
npx opensight-mcp health
# or
vlm health

# Analyze an image
vlm describe --image screenshot.png --prompt "What errors are visible?"

# Extract text (OCR)
vlm ocr --image document.png --engine vlm

# Find text with coordinates
vlm find --image app.png --query "Submit button"

🤖 Recommended Models

Model	Size	Best For
`minicpm-v:latest`	~5.5 GB	Default. General analysis, OCR, UI. Fast and accurate.
`llava:7b`	~4 GB	Lightweight fallback for limited VRAM
`gemini-2.0-flash`	Cloud	Free tier, Google quality
`qwen/qwen2.5-vl-32b-instruct:free`	Cloud	Free tier via OpenRouter
`gpt-4o`	Cloud	Best quality (paid)

🔧 Development

git clone https://github.com/Mr-JoE1/opensight-mcp.git
cd opensight-mcp
npm install
npm test                 # 21 unit tests via node:test
npm run test:watch       # Watch mode

opensight-mcp/
├── vision-mcp.mjs          # Main MCP server (8 tools)
├── vlm.mjs                 # CLI tool
├── src/
│   ├── helpers.mjs         # Pure utility functions (tested)
│   └── providers.mjs       # Multi-backend abstraction
├── tests/
│   └── helpers.test.mjs    # 21 unit tests
└── opensight-wrapper.sh    # MCP wrapper with env defaults

📄 License

MIT — see LICENSE.

Made for coding agents. Private by default. Cloud when you need it.

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Frenchie A
io.github.Lab94
OCR, transcription, file extraction, and image generation for AI agents via MCP.
AI & Machine Learning Image & Video Processing Speech Processing
72
mcp-qwen-image
io.github.AceDataCloud
MCP server for Qwen Image 3 AI image generation
AI & Machine Learning Image & Video Processing
1
toolweave
io.github.andreysparish
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
App Automation AI & Machine Learning Agent Orchestration
2
Writingmate MCP
ai.writingmate
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
AI & Machine Learning Image & Video Processing
1

Related MCP Servers

mcp-vision
Image & Video Processing AI & Machine Learning
MikeyBeez
F
license
A
quality
D
maintenance
MCP server for vision capabilities, enabling screenshot, camera, and image analysis using Ollama vision models.
Updated 8 months ago (2026-01-14 19:30 UTC)
4
1
pic-id-mcp
Image & Video Processing AI & Machine Learning
HaoyueQin
A
license
Not graded
quality
A
maintenance
Local vision-capable MCP server that lets AI agents describe screenshots, UI, charts, and photos via vision and OCR tools, with support for multiple providers and automatic fallback.
Updated a month ago (2026-08-09 10:05 UTC)
6
MIT
mcp-six-eyes
Image & Video Processing AI & Machine Learning
RimunAce
A
license
A
quality
A
maintenance
MCP server that gives text-only AI agents the ability to understand images via vision tools, including multi-image analysis, OCR, comparison, and structured extraction. It uses providers like OpenAI, Anthropic, Gemini, and OpenRouter to return plain text descriptions.
Updated 8 days ago (2026-08-26 16:12 UTC)
4
10
177
MIT
vision-mcp
Image & Video Processing AI & Machine Learning
weekitmo
A
license
A
quality
B
maintenance
Vision MCP enables text-only agents to understand images through any OpenAI-compatible vision model. It supports local images, URLs, screenshots, documents, charts, and code errors with tools like analyze_image and understand_image.
Updated 21 days ago (2026-08-14 07:29 UTC)
2
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Mr-JoE1/opensight-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server