shotapi-mcp-server
Web screenshot and HTML rendering MCP Server for AI Agents. One command, zero install.
Documentation
ShotAPI — Web Screenshot & Render MCP Server for AI Agents
Give your AI Agent eyes. One command, zero install.
Quick Start (Remote Mode — No Install)
# Claude Code
claude mcp add --transport streamable-http shotapi https://aiphotoshop.mynatapp.cc/mcp
# Or with npx
npx -y @anthropic-ai/claude-code@latest --mcp https://aiphotoshop.mynatapp.cc/mcpFor Claude Desktop / Cursor, add to your config:
{
"mcpServers": {
"shotapi": {
"type": "streamable-http",
"url": "https://aiphotoshop.mynatapp.cc/mcp"
}
}
}Real Use Cases
1. Claude verifies its own code
Human: Build a landing page with a hero section, testimonials, and pricing grid.
Claude: [writes HTML/CSS code]
Claude: Let me check this with the render tool...
[Claude calls ShotAPI render tool with the HTML it wrote]
Claude: The pricing grid overlaps on mobile. Fixing responsive breakpoints...2. Deployment verification
Human: I just deployed. Check if it looks right.
Claude: [calls ShotAPI screenshot on https://yourapp.com]
Claude: Footer text is cut off — CSS overflow issue. Background image 404.3. UI regression in CI/CD
# Capture before/after screenshots and compare
curl -s "https://aiphotoshop.mynatapp.cc/v1/screenshot?url=https://staging.myapp.com" -o before.png
curl -s "https://aiphotoshop.mynatapp.cc/v1/screenshot?url=https://staging.myapp.com" -o after.png3 MCP Tools
| Tool | Description | Example |
|---|---|---|
| `screenshot_one_liner` | One URL, one screenshot | `screenshot_one_liner(url="https://github.com")` |
| `screenshot` | Full control: viewport, full-page, CSS selector, format | `screenshot(url="https://github.com", selector="#hero")` |
| `render` | Render HTML/CSS to image — Agent writes code, sees result instantly | `render(html="Hello")` |
The `render` tool closes the feedback loop: write code → render → see → revise → render again.
Why ShotAPI?
- MCP-native — No glue code. Agent calls tools directly in conversation.
- Zero install remote mode — streamable-http, no Python/Playwright needed.
- Direct China access — No VPN required.
- Free tier — 50 screenshots + 50 renders/month, IP-based, no signup, no API key. All features unlocked (full-page, selector, WebP).
- Render capability — Not just screenshots of existing pages. Render Agent-generated HTML.
- Built-in ad blocking — Cleaner screenshots, less noise.
- Listed in MCP Registry — Official Anthropic MCP server directory.
Try It Now (No Signup)
curl -s "https://aiphotoshop.mynatapp.cc/v1/screenshot?url=https://github.com" -o shot.jpgPricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50+50/month (IP-based, all features, no signup) |
| Starter | $4.90/mo | 5,000/month |
| Pro | $9.90/mo | 20,000/month |
Free tier: no API key needed. Paid: get key at pricing page.
Local Mode (STDIO)
For private deployments or paid-tier usage, run locally:
# Install dependencies
pip install -r requirements.txt
playwright install chromium
# Set env vars
export SHOTAPI_BASE_URL=https://aiphotoshop.mynatapp.cc
export SHOTAPI_KEY=your_key_here # optional for paid tiers
# Add to Claude Code
claude mcp add shotapi python mcp_stdio.pyLinks
- Docs: https://aiphotoshop.mynatapp.cc/docs
- Pricing: https://aiphotoshop.mynatapp.cc/pricing
- Health: https://aiphotoshop.mynatapp.cc/health
- MCP Registry: https://registry.modelcontextprotocol.io/servers/io.github.smallhandsome/shotapi-mcp-server
- Smithery: https://smithery.ai/server/@ljs/shotapi
- awesome-mcp-servers: https://github.com/punkpeye/awesome-mcp-servers
- Dev.to Article: https://dev.to/smallhandsome/give-your-ai-agent-eyes-building-a-visual-mcp-server-for-web-screenshots-3f49
Frequently asked questions
What is shotapi-mcp-server?
shotapi-mcp-server is Web screenshot and HTML rendering MCP Server for AI Agents. One command, zero install.
How do I install shotapi-mcp-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is shotapi-mcp-server open source?
Yes — it is hosted on GitHub at https://github.com/smallhandsome/shotapi-mcp-server and has 1 stars.
Related MCP tools
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.
Open-source coding agent memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth! Python-based implementation. Trusted by 11000+ developers.
Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace MCP Server & CLI Tool
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP