//MCP server\\
Web data for your AI agent, one tool call away
Your agent finds an Actor, runs it, and reads the results.
Claude- ChatGPT
- Codex
- Cursor
VS Code- Windsurf
- Cline
- Zed
//What is MCP\\
Ask in plain words. Get a dataset back.
MCP is the open standard AI assistants use to call tools.
//Why Scrape.ly\\
Built for agents
Every Actor is a tool
Fields, not HTML
Capped spend
Setup
One URL, every client
Pick your client and copy the config, or let your agent set it up.
https://api.scrape.ly/mcpCustomize → Connectors → Add custom connectorhttps://api.scrape.ly/mcpclaude mcp add --transport http scrapely https://api.scrape.ly/mcpclaude mcp add --transport http scrapely https://api.scrape.ly/mcp \
--header "Authorization: Bearer YOUR_API_KEY"chatgpt.com/plugins → Add custom MCP server
https://api.scrape.ly/mcpRun in your terminal
codex mcp add scrapely --url https://api.scrape.ly/mcp
codex mcp login scrapely[mcp_servers.scrapely]
url = "https://api.scrape.ly/mcp"
# Reads the API key from this environment variable
bearer_token_env_var = "SCRAPELY_API_KEY"~/.cursor/mcp.json
{
"mcpServers": {
"scrapely": {
"url": "https://api.scrape.ly/mcp"
}
}
}{
"mcpServers": {
"scrapely": {
"url": "https://api.scrape.ly/mcp",
"headers": {
"Authorization": "Bearer ${env:SCRAPELY_API_KEY}"
}
}
}
}{
"servers": {
"scrapely": {
"type": "http",
"url": "https://api.scrape.ly/mcp"
}
}
}{
"inputs": [
{
"type": "promptString",
"id": "scrapely-key",
"description": "Scrape.ly API key",
"password": true
}
],
"servers": {
"scrapely": {
"type": "http",
"url": "https://api.scrape.ly/mcp",
"headers": {
"Authorization": "Bearer ${input:scrapely-key}"
}
}
}
}~/.config/devin/mcp_config.json
{
"mcpServers": {
"scrapely": {
"serverUrl": "https://api.scrape.ly/mcp"
}
}
}{
"mcpServers": {
"scrapely": {
"serverUrl": "https://api.scrape.ly/mcp",
"headers": {
"Authorization": "Bearer ${env:SCRAPELY_API_KEY}"
}
}
}
}MCP Servers → Configure
{
"mcpServers": {
"scrapely": {
"type": "streamableHttp",
"url": "https://api.scrape.ly/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
},
"disabled": false,
"autoApprove": []
}
}
}Zed settings.json
{
"context_servers": {
"scrapely": {
"url": "https://api.scrape.ly/mcp"
}
}
}{
"context_servers": {
"scrapely": {
"url": "https://api.scrape.ly/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Streamable HTTP · OAuth or Bearer key
URL: https://api.scrape.ly/mcp
Header: Authorization: Bearer YOUR_API_KEY22 tools, on by default
Actors
- search-actors
- fetch-actor-details
- call-actor
Runs
- get-actor-run
- get-actor-run-list
- get-actor-log
- abort-actor-run
Storage
- get-dataset-items
- get-dataset
- get-dataset-schema
- +5 more
Tasks
- create-actor-task
- update-actor-task
- publish-actor-task
- +2 more
Docs
- search-scrapely-docs
- fetch-scrapely-docs
//Examples\\
Prompts to try
Build a lead list
Find 30 dental clinics in Austin on Google Maps that list a public email address, and put them in a table with name, email, and rating.
Research a search result page
Search Google for "best CRM for startups" and give me the top 10 organic results with title and URL.
//Security & pricing\\
You stay in control
OAuth
Tokens expire in 24 hours.
API key
Or a Bearer header. Rotate any time.
Spend caps
Limit items or dollars per run.
Free server
You pay only for runs.
//FAQ\\
FAQ
The short answers.
Do I need an API key?
Not with most clients: they sign you in with OAuth. Otherwise, send your API key as a Bearer header.
What does it cost?
The server is free on every plan. Runs are billed like any other run.
Give your agent the web.
Connect in a minute.
The web's data, in your hands.
Powered by Evomi infrastructure.
Powered by Evomi infrastructure.
© 2026 TeraShift GmbH
All services online