# Scrape.ly

> Scrape.ly is a freemium MCP server for web search and scraping. Find, run and read results from Scrape.ly Actors inside any MCP client. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $19 a month
- **Platforms:** API, CLI, self-hosted
- **Website:** https://scrape.ly/docs/mcp
- **Repository:** https://github.com/scrapely-app/scrapely-mcp
- **MCP Registry name:** ly.scrape/scrapely-mcp-server
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-14

## About

Tools are grouped into categories: actors, docs, runs and storage. A `--tools` flag swaps the default set for the categories or tool names you pick, and `--actors user/actor` can expose a specific Actor as its own tool.

The hosted endpoint at mcp.scrape.ly uses streamable HTTP and signs you in with OAuth 2.1 and PKCE, or accepts a bearer token from the dashboard. Agents without an account can pay per call in USDC through x402. A Python package, `scrapely-mcp`, runs the same server over stdio for clients that cannot reach a remote server.

The server acts with your token's permissions, so an agent can start paid runs. The docs suggest scoped API keys, such as a read-only preset, to limit what it can do.

## Features

- **Actor search and run:** Look up Actors in the Store, read their details and start them with call-actor.
- **Run monitoring:** Check run status, list recent runs, read logs or abort a run.
- **Dataset and store access:** Read dataset items and schemas and key-value store records from finished runs.
- **OAuth or token sign-in:** Connect with OAuth, a bearer token or a query-parameter token.
- **Scoped API keys:** Limit an agent to permissions such as actors:run and datasets:read.
- **Remote or local:** Use the hosted endpoint or the stdio Python package.

## Good for

- Run a Google Maps or social scraper from a chat and read the results back
- Let an agent poll a long scraping run and fetch its log
- Give a read-only key to an agent that only needs to inspect stored datasets
- Search the Scrape.ly docs from within the coding assistant

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http scrapely-mcp-server https://mcp.scrape.ly
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.scrape.ly
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "scrapely-mcp-server": {
      "url": "https://mcp.scrape.ly"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "scrapely-mcp-server": {
      "type": "http",
      "url": "https://mcp.scrape.ly"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "scrapely-mcp-server": {
      "serverUrl": "https://mcp.scrape.ly"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "scrapely-mcp-server": {
      "type": "http",
      "url": "https://mcp.scrape.ly"
    }
  }
}
```

## Tools

- `search-actors`: Search the Store for Actors.
- `fetch-actor-details`: Read details of an Actor.
- `call-actor`: Run an Actor.
- `search-scrapely-docs`: Search the documentation.
- `fetch-scrapely-docs`: Fetch a documentation page.
- `get-actor-run`: Read the state of a run.
- `get-actor-output`: Read a run's output.
- `get-actor-run-list`: List runs.
- `get-actor-log`: Read a run's log.
- `abort-actor-run`: Stop a running Actor.
- `get-dataset`: Read dataset metadata.
- `get-dataset-items`: Read items from a dataset.
- `get-dataset-schema`: Read a dataset's schema.
- `get-key-value-store`: Read a key-value store.

## FAQ

### How do I authenticate?

Use OAuth when your client supports it, a bearer token from Settings, API & Integrations, or a token in the URL query string. The docs advise a header over the query string because URLs end up in logs.

### Can I restrict what the agent does?

Yes. Create a scoped API key, for example the read-only preset, or limit it to actors:run, runs:read, datasets:read and keyValueStores:read.

### Is there a local version?

Yes. The scrapely-mcp Python package runs over stdio and reads SCRAPELY_TOKEN from the environment.

### Does the MCP server cost extra?

The pricing page lists the MCP server on every plan, including Free, which comes with $5 of usage a month. Runs themselves are billed from your prepaid balance.

### Is Scrape.ly free?

Scrape.ly has a free plan, with paid plans for more usage or features. Paid plans start at $19 a month.

### How do I add Scrape.ly to Claude Code?

Run this command in your terminal: claude mcp add --transport http scrapely-mcp-server https://mcp.scrape.ly

### What are the best alternatives to Scrape.ly?

The closest alternatives to Scrape.ly are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.
- [Shopify MCP Server (any store)](https://ai-powered.com/mcp/shopify-mcp-server-any-store): Shopify MCP Server (any store) is a paid MCP server for e-commerce.
- [Chanroll: YouTube Channel Video Scraper (Official API)](https://ai-powered.com/mcp/chanroll-youtube-channel-video-scraper-official-api): Chanroll: YouTube Channel Video Scraper (Official API) is a paid MCP server for design and media.
- [Vidvett: YouTube Video Details Scraper (Official API)](https://ai-powered.com/mcp/vidvett-youtube-video-details-scraper-official-api): Vidvett: YouTube Video Details Scraper (Official API) is a paid MCP server for design and media.

---
Source: https://ai-powered.com/mcp/scrape-ly
