Peekaboo
The Peekaboo MCP Server enables your AI assistant to analyze content on macOS and capture screenshots with high precision.
Features
- 👁️ Bug Hunting: Capture and analyze UI issues instantly.
- 📸 Instant Analysis: Take screenshots and ask questions in one step.
- 🎨 Design Reviews: Let AI critique your designs with visual evidence.
- 📊 Data Analysis: Extract insights from charts and graphs.
- 📱 Multi-Screen Capture: Target specific windows or entire screens.
- 🤖 Automation: Enable AI to see and act on visual data.
- 🔮 AI Integration: Supports Ollama and OpenAI for advanced analysis.
Use Cases
- Debugging UI Issues: Quickly capture and share visual bugs with your team or AI assistant.
- Design Feedback: Get instant feedback on layouts, colors, and design elements.
- Data Extraction: Analyze charts, graphs, and visual data for insights.
- Automated Testing: Verify app UI consistency across multiple screens.
How to Use It
1. Ensure your system meets the requirements:
- macOS 14.0+ (Sonoma or later)
- Node.js 20.0+
2. Install Peekaboo globally:
npx -y @steipete/peekaboo-mcp@beta3. Configure your MCP client:
{
"mcpServers": {
"peekaboo": {
"command": "npx",
"args": ["-y", "@steipete/peekaboo-mcp@beta"],
"env": {
"PEEKABOO_AI_PROVIDERS": "ollama/llava:latest"
}
}
}
}4. Restart your MCP client.
Usage
Capture a Screenshot:
{
"tool_name": "image",
"arguments": {
"mode": "screen",
"path": "~/Desktop/screenshot.png",
"format": "png"
}
}Analyze an Image:
{
"tool_name": "analyze",
"arguments": {
"image_path": "~/Desktop/screenshot.png",
"question": "What’s wrong with this UI?"
}
}List Running Applications:
{
"tool_name": "list",
"arguments": {
"item_type": "running_applications"
}
}FAQs
Q: What AI models does Peekaboo support?
A: Peekaboo supports Ollama (e.g., LLaVA) and OpenAI (e.g., GPT-4). You can configure multiple providers in the PEEKABOO_AI_PROVIDERS environment variable.
Q: How do I troubleshoot permission issues?
A: Grant Screen Recording and Accessibility permissions in System Preferences → Security & Privacy → Privacy. Restart your application after making changes.
Q: Can I use Peekaboo without an AI provider?
A: Yes, you can use it solely for capturing screenshots. AI analysis is optional.
Q: How do I capture a specific window?
A: Use the app argument in the image tool to target a specific application window.
Q: Where are screenshots saved?
A: By default, screenshots are saved to ~/Pictures/PeekabooCaptures. You can customize this path using the PEEKABOO_DEFAULT_SAVE_PATH environment variable.
Latest MCP Servers
CVE
WebMCP
webmcp is an MCP server that connects MCP clients to web search, page fetching, and local LLM-based extraction. It’s ideal…
Google Meta Ads GA4
Featured MCP Servers
Notion
Claude Peers
Excalidraw
FAQs
Q: What exactly is the Model Context Protocol (MCP)?
A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.
Q: How is MCP different from OpenAI's function calling or plugins?
A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.
Q: Can I use MCP with frameworks like LangChain?
A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.
Q: Why was MCP created? What problem does it solve?
A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.
Q: Is MCP secure? What are the main risks?
A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.
Q: Who is behind MCP?
A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.
