Integrations

Claude Code

Add Scrape.ly to Claude Code with one command.

Add Scrape.ly to Claude Code: in the terminal, Claude can search the Store, run Actors, wait for their runs, and read the results while it works on your code. It connects to the hosted MCP server with one command.

Add the server

.bash

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

Then start Claude Code, run /mcp, choose scrapely, and pick Authenticate: a dashboard window opens where you sign in and approve access, so there is no token to copy.

The server is added for the current project. Add --scope user to use it in every project, or --scope project to write it to the project's .mcp.json so your team gets it too.

Use an API key instead

To skip the sign-in, or to cap spending, pass a key from Settings → API & Integrations in the dashboard as a header:

.bash

claude mcp add --transport http scrapely https://mcp.scrape.ly \
  --header "Authorization: Bearer YOUR_TOKEN"

Claude can do anything the key can, including starting paid runs, so give it a scoped key: actors:run, runs:read, and datasets:read, with a Max charge per day. See API keys & permissions. Don't use --scope project with a key: it would be written to .mcp.json.

Use it in a session

Start claude in your project and ask:

.text

Find an Actor that scrapes Google Maps, run it for 'coffee shops in Berlin' with at most 20 results, and save the name, rating, and address of each place to places.json.

Claude asks before each tool call unless you allow the Scrape.ly tools in its permissions.

What Claude can do

Claude gets the MCP server's default tools. The ones used most:

Tool	What it does
`search-actors`	Find Actors in the Store by keywords.
`fetch-actor-details`	Read an Actor's input schema, README, and pricing before running it.
`call-actor`	Run an Actor with a JSON input, optionally with `maxItems` and `maxTotalChargeUsd`.
`get-actor-run`	Wait for a run and check its status.
`get-actor-output`	Read a run's results, paged and kept compact.

The full list, including saved inputs and automations, is on the MCP server page. To run one Actor you already know, name it in the prompt, for example Run username/actor-name, so Claude skips the search.

For Claude in the browser or the desktop app, add Scrape.ly as a connector instead: see Claude Desktop.

Costs: runs started by Claude are billed like any run. Put the limits in the prompt (such as "at most 20 results"). A Max charge per day applies only to API keys, not to an OAuth sign-in.