Scrapfly MCP Server
Give your AI real-time access to any website
๐ Landing Page โข
๐ Documentation โข
๐ฎ Live Demo โข
๐ Get API Key
At a glance
| |
|---|
| Remote server | https://mcp.scrapfly.io/mcp (streamable HTTP, nothing to install) |
| Self-hosted | Go binary (stdio or -http) or the Docker image of this repo, see Self-Hosted below |
| stdio-only clients | npx mcp-remote https://mcp.scrapfly.io/mcp |
| Authentication | OAuth2 sign-in on the remote server, or a Scrapfly API key (SCRAPFLY_API_KEY, Authorization: Bearer <key>) |
| Tools | 62: web scraping (5), account (2), Cloud Browser sessions (9), page interaction (17), WebMCP (2), credential vaults (15), alerts (12). Full list under Available Tools below. |
Add it to any MCP client:
{
"mcpServers": {
"scrapfly": { "type": "http", "url": "https://mcp.scrapfly.io/mcp" }
}
}
Tools that fetch pages need no setup beyond the key: web_get_page (quick fetch), web_scrape (full control: JS rendering, proxy pool, country, extraction) and screenshot.
What is Scrapfly MCP?
The Scrapfly MCP Server connects your AI assistants to live web data through the Model Context Protocol. Transform your AI from being limited by training data to having real-time access to any website.
โจ What Your AI Can Do
| Capability | Description |
|---|
| ๐ Scrape Live Data | Pull current prices, listings, news, or any webpage content in real-time |
| ๐ก๏ธ Bypass Anti-Bot Systems | Automatically handle CAPTCHAs, proxies, JavaScript rendering, and rate limits |
| โก Extract Structured Data | Parse complex websites into clean JSON using AI-powered extraction |
| ๐ธ Capture Screenshots | Take visual snapshots of pages or specific elements for analysis |
๐ Why Scrapfly?
Built on battle-tested infrastructure used by thousands of developers:
๐ Learn more: Why Scrapfly MCP?
๐ Quick Install
Click one of the buttons below to install the MCP server in your preferred IDE:

๐ฆ Manual Installation
Standard Configuration
Works with most MCP-compatible tools:
{
"servers": {
"scrapfly-cloud-mcp": {
"type": "http",
"url": "https://mcp.scrapfly.io/mcp"
}
}
}
Cloud Configuration (NPX)
For tools that require a local process:
{
"mcpServers": {
"scrapfly": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.scrapfly.io/mcp"
]
}
}
}
๐ง IDE-Specific Setup
VS Code
One-Click Install

Manual Install
Follow the VS Code MCP guide or use the CLI:
code --add-mcp '{"name":"scrapfly-cloud-mcp","type":"http","url":"https://mcp.scrapfly.io/mcp"}'
After installation, Scrapfly tools will be available in GitHub Copilot Chat.
๐ Full guide: VS Code Integration
VS Code Insiders
One-Click Install

Manual Install
code-insiders --add-mcp '{"name":"scrapfly-cloud-mcp","type":"http","url":"https://mcp.scrapfly.io/mcp"}'
๐ Full guide: VS Code Integration
Visual Studio
One-Click Install

Manual Install
- Open Visual Studio
- Navigate to GitHub Copilot Chat window
- Click the tools icon (๐ ๏ธ) in the chat toolbar
- Click + Add Server to open the configuration dialog
- Configure:
- Server ID:
scrapfly-cloud-mcp
- Type:
http/sse
- URL:
https://mcp.scrapfly.io/mcp
- Click Save
๐ Full guide: Visual Studio MCP documentation
Cursor
One-Click Install

Manual Install
- Go to
Cursor Settings โ MCP โ Add new MCP Server
- Use the standard configuration above
- Click Edit to verify or add arguments
๐ Full guide: Cursor Integration
Claude Code
Use the Claude Code CLI:
claude mcp add scrapfly-cloud-mcp --url https://mcp.scrapfly.io/mcp
๐ Full guide: Claude Code Integration
Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"scrapfly": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.scrapfly.io/mcp"]
}
}
}
๐ Full guide: Claude Desktop Integration
Cline
Add to your Cline MCP settings:
{
"scrapfly-cloud-mcp": {
"type": "http",
"url": "https://mcp.scrapfly.io/mcp"
}
}
๐ Full guide: Cline Integration
Windsurf
Follow the Windsurf MCP documentation using the standard configuration.
๐ Full guide: Windsurf Integration
Zed
Add to your Zed settings:
{
"context_servers": {
"scrapfly-cloud-mcp": {
"type": "http",
"url": "https://mcp.scrapfly.io/mcp"
}
}
}
๐ Full guide: Zed Integration
OpenAI Codex
Create or edit ~/.codex/config.toml:
[mcp_servers.scrapfly-cloud-mcp]
url = "https://mcp.scrapfly.io/mcp"
๐ More info: Codex MCP documentation
Gemini CLI
Follow the Gemini CLI MCP guide using the standard configuration.
OpenCode
Add to ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"scrapfly-cloud-mcp": {
"type": "http",
"url": "https://mcp.scrapfly.io/mcp",
"enabled": true
}
}
}
๐ More info: OpenCode MCP documentation
The Scrapfly MCP Server exposes 62 tools in seven groups. Most tasks need only the first group.
Web scraping (5)
Stateless, one call per page.
| Tool | Description | Use Case |
|---|
scraping_instruction_enhanced | Cheat-sheet of the scraping options | Optional, when the right options are unclear |
web_get_page | Quick page fetch with smart defaults | Simple scraping tasks |
web_scrape | Full control: headers, JS rendering, country, proxy pool, extraction | Complex scraping, login flows |
screenshot | One-shot PNG of a URL | Visual analysis, monitoring |
check_if_blocked | Decide whether a scrape result is a block page | Retry or escalate the proxy pool |
Account (2)
| Tool | Description |
|---|
info_account | Subscription plan, API credit usage, concurrency |
info_api_key | The API key this server is authenticated with |
Cloud Browser sessions (9)
A stateful real browser, kept between calls.
| Tool | Description |
|---|
cloud_browser_open | Start a session at a URL |
browser_unblock | Same, through the anti-bot bypass first |
cloud_browser_navigate | Load a new URL in the open session |
cloud_browser_sessions | List active sessions |
cloud_browser_close | Close the session |
cloud_browser_screenshot | PNG of the session, optionally of a CSS selector |
cloud_browser_eval | Run JavaScript and return its value |
cloud_browser_downloads | Files downloaded during the session |
cloud_browser_performance | PageSpeed-style lab run with mobile throttling |
Page interaction (17)
Act on the open Cloud Browser session. Elements are addressed by the uid that take_snapshot returns.
take_snapshot, take_screenshot, find_elements, get_page_url, evaluate_script, click, hover, drag, fill, type_text, press_key, select_option, dropdown_options, scroll, scroll_to_text, go_back, wait
WebMCP (2)
For pages that register their own tools with navigator.modelContext.
list_webmcp_tools, call_webmcp_tool
Credential vaults (15)
Store logins for Cloud Browser sessions, optionally mirrored from 1Password.
cloud_browser_vault_create, cloud_browser_vault_list, cloud_browser_vault_get, cloud_browser_vault_update, cloud_browser_vault_delete, cloud_browser_vault_rotate, cloud_browser_vault_item_create, cloud_browser_vault_item_list, cloud_browser_vault_item_update, cloud_browser_vault_item_delete, cloud_browser_vault_service_link, cloud_browser_vault_service_update, cloud_browser_vault_service_sync, cloud_browser_vault_service_test, cloud_browser_vault_service_unlink
Alerts (12)
Create, test and snooze alert rules on your account metrics. Writes take a confirm step.
alert_metric_families, alert_preview, alert_create, alert_update, alert_delete, alert_get, alert_list, alert_count_active, alert_series, alert_test, alert_snooze, alert_unsnooze
๐ Full reference: Tools & API Specification
Proxy pools
web_scrape and web_get_page take a proxy_pool: public_datacenter_pool,
public_residential_pool, or public_tor_pool for the Tor network (.onion). Without one, the API
picks its default. The Unblocker (anti-bot bypass) is the unblocker input of web_scrape, on when
omitted; web_get_page always runs with it.
Example: Scrape a Page
User: "What are the top posts on Hacker News right now?"
AI: Uses web_get_page to fetch https://news.ycombinator.com and returns current top stories
User: "Get all product prices from this Amazon page"
AI: Uses web_scrape with extraction_model="product_listing" to return structured JSON
๐ More examples: Real-World Examples
๐ Authentication
Scrapfly MCP supports multiple authentication methods:
๐ Get your API key: Scrapfly Dashboard
๐ Configuration Reference
| Setting | Value |
|---|
| Server Name | scrapfly-cloud-mcp |
| Type | Remote HTTP Server |
| URL | https://mcp.scrapfly.io/mcp |
| Protocol | MCP over HTTP/SSE |
๐ฅ๏ธ Self-Hosted / Local Deployment
You can run the Scrapfly MCP server locally or self-host it.
CLI Arguments
| Flag | Description |
|---|
-http <address> | Start HTTP server at the specified address (e.g., :8080). Takes precedence over PORT env var. In server-key mode this binds loopback (127.0.0.1) unless you also pass -allow-remote. |
-apikey <key> | Use this API key instead of the SCRAPFLY_API_KEY environment variable. |
-allow-remote | Server-key HTTP mode only: permit binding a non-loopback interface. That mode performs no per-caller authentication โ every request uses the baked-in key โ so only enable this behind your own auth proxy. |
-verify-ssl | Verify TLS certificates on outbound calls (default true). Set false only when targeting a host that serves a self-signed certificate. |
Environment Variables
| Variable | Description |
|---|
PORT | HTTP port to listen on. Used if -http flag is not set. |
SCRAPFLY_API_KEY | Scrapfly API key baked into the server. When set, the server uses it for every request (server-key mode) and does not read a per-request key. |
SCRAPFLY_ALLOW_REMOTE | 1/true is the env equivalent of -allow-remote. |
SCRAPFLY_VERIFY_SSL | 0/false is the env equivalent of -verify-ssl=false. |
Per-request key: start the server without a baked-in key (-http only) and
each caller supplies their own key per request โ as Authorization: Bearer <key>,
or ?key=<key> / ?apiKey=<key>. This path is authenticated; the server-key
path above is not, which is why it stays on loopback by default.
Examples
./scrapfly-mcp -http :8080
PORT=8080 ./scrapfly-mcp
SCRAPFLY_API_KEY=... ./scrapfly-mcp -http :8080
SCRAPFLY_API_KEY=... ./scrapfly-mcp -http 0.0.0.0:8080 -allow-remote
./scrapfly-mcp
Docker
docker build -t scrapfly-mcp .
docker run -p 8080:8080 scrapfly-mcp
docker run -e PORT=9000 -p 9000:9000 scrapfly-mcp
๐ค Framework Integrations
Scrapfly MCP also works with AI frameworks and automation tools:
๐ All integrations: Integration Index
๐ Resources
๐ฌ Need Help?
Made with โค๏ธ by Scrapfly
The Web Scraping API for Developers