For AI agents · Model Context Protocol
SnapshotFlow MCP Server
Give your AI agent a screenshot tool it can call directly. The SnapshotFlow MCP server exposes SnapshotFlow's rendering engine over the Model Context Protocol, so agents like Claude and Cursor can capture, batch, and compare web pages without scraping HTML or scripting a browser.
Connect your agent
The recommended remote MCP endpoint is served directly by the SnapshotFlow backend:
https://api.snapshotflow.com/mcp
Add it to your client's MCP configuration — for example claude_desktop_config.json or Cursor MCP settings:
{
"mcpServers": {
"snapshotflow": {
"url": "https://api.snapshotflow.com/mcp"
}
}
}
The endpoint is protected by OAuth 2.0. On first connect, your MCP client opens a browser to sign in and is issued a short-lived Bearer token automatically — no API key header to manage. Requests without a valid token return 401 missing_token.
A local stdio wrapper is also available for development. Full setup instructions live in the MCP section of the API docs.
Available MCP tools
Every tool and its full input schema is described in the MCP server card.
screenshot— capture a URL or base64 HTML as PNG/JPEG/WebP. Supports full-page capture, dark mode, selector waits, ad & cookie-banner blocking, content extraction, and metadata.batch_screenshot— capture 1–10 URLs in one parallel request to compare, audit, or survey multiple pages.visual_diff— pixel-compare two URLs and return a highlighted diff image plus change statistics.extract_text— fetch a URL and return its content as Markdown, plain text, or raw HTML — no screenshot, far cheaper in LLM tokens when you only need text.check_job— check the status of an async screenshot job and retrieve its result.
What agents use it for
AI agents working on web tasks frequently need to see a rendered page rather than guess from raw HTML. With the MCP server connected, an agent can capture a live page during a coding task, diff a deploy against its baseline for visual regressions, batch-survey a list of URLs, and pull clean page content or metadata — all as native tool calls.
Machine-readable discovery
The MCP server card lets agents and registries discover SnapshotFlow's tools automatically:
https://snapshotflow.com/.well-known/mcp/server-card.json
It follows the MCP server-card schema and lists each tool's name, description, and JSON input schema.
Make your AI agent web-aware
Connect the SnapshotFlow MCP server in minutes. Free tier: 300 screenshots for the lifetime of the account. No credit card.
Frequently asked questions
What is the SnapshotFlow MCP server?
It is a Model Context Protocol server that exposes SnapshotFlow's screenshot engine as native tools — screenshot, batch_screenshot, visual_diff, extract_text, and check_job — so AI agents like Claude and Cursor can capture, compare, and read web pages directly.
Which MCP endpoint should I use?
The recommended remote MCP endpoint is https://api.snapshotflow.com/mcp. A local stdio wrapper is also available for development.
Is there a machine-readable MCP server card?
Yes. The MCP server card is published at /.well-known/mcp/server-card.json and describes every tool and its JSON input schema.
Learn more
- What is the best Screenshot API for AI agents? — how MCP and WebMCP compare
- WebMCP explained — in-browser tools vs the remote MCP server
- MCP tool deep-dive: extracting text 10× cheaper than a screenshot
- MCP server reference — endpoints, auth, and the full tool list