Scrapewise

ScrapeWise MCP Server

Scrape, clean and match product and price data from any website — from inside your AI agent.

ScrapeWise runs a hosted Model Context Protocol server. You point your MCP client at one URL and add your API key. Your agent can then read product and price data from any shop or from Amazon, find local businesses, search Google and Amazon, fetch web pages and read the rows saved in your account. Add ?toolsets=outcome,admin to the URL and it also builds and runs scrapers.

• Endpoint: https://mcp.scrapewise.ai/mcp
• Endpoint with the setup tools (to build scrapers): https://mcp.scrapewise.ai/mcp?toolsets=outcome,admin
• Transport: Streamable HTTP
• Registry name: ai.scrapewise/scrapewise (official MCP registry)
• Auth: Authorization: Bearer <your API key>
• Docs: scrapewise.ai/mcp

This repository holds the connection manifest and the per-client config for that server. The server itself is hosted — there is nothing here to install or run.

Get an API key

Sign up at scrapewise.ai, then go to Settings → API Keys and create one. Pricing is pay-as-you-go.

Connect

Replace YOUR_SCRAPEWISE_API_KEY in every snippet below.

These snippets connect to the short list of data tools. To build scrapers as well, use this address in the same place:

https://mcp.scrapewise.ai/mcp?toolsets=outcome,admin

An account that gets its first MCP key now sees only the short list at the bare address. Accounts that still hold an older MCP key keep every tool. The choice is read when the session starts, so reconnect after changing it. Spell it toolsets: a misspelt switch is ignored without an error.

Claude Code

claude mcp add scrapewise --transport http https://mcp.scrapewise.ai/mcp \
  --header 'Authorization: Bearer YOUR_SCRAPEWISE_API_KEY'

With the setup tools. The single quotes are needed: in zsh an unquoted ? breaks the command.

claude mcp add scrapewise --transport http 'https://mcp.scrapewise.ai/mcp?toolsets=outcome,admin' \
  --header 'Authorization: Bearer YOUR_SCRAPEWISE_API_KEY'

Claude Desktop

claude_desktop_config.json:

{
  "mcpServers": {
    "scrapewise": {
      "url": "https://mcp.scrapewise.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_SCRAPEWISE_API_KEY"
      }
    }
  }
}

Cursor

Same shape, in ~/.cursor/mcp.json:

{
  "mcpServers": {
    "scrapewise": {
      "url": "https://mcp.scrapewise.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_SCRAPEWISE_API_KEY"
      }
    }
  }
}

VS Code

VS Code is the odd one out: the map is servers, not mcpServers, and a remote server has to name its transport with "type": "http". Get either wrong and VS Code skips the entry without telling you.

Open the Command Palette → MCP: Open User Configuration, then:

{
  "servers": {
    "scrapewise": {
      "type": "http",
      "url": "https://mcp.scrapewise.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_SCRAPEWISE_API_KEY"
      }
    }
  }
}

Anything else

Any client that speaks Streamable HTTP works. Give it the endpoint, the Authorization header, and the name scrapewise.

What your agent can do

With the setup tools (?toolsets=outcome,admin)

Tools

The server advertises its own tool list once connected, so this is a reference rather than the source of truth. What a given API key sees can differ — by the address you connect to, and by the key's own access level. Full documentation at docs.scrapewise.ai.

Default tools (an account's first key)

get_product_data · get_amazon_product · clean_product_data · find_local_businesses · google_search · search_amazon · google_trends · fetch_page · get_results · cancel_job · scrapewise_get_scraper_group_list · scrapewise_get_scraper_data_group_client

Every paid tool states its price and takes quote_only: true, which returns the price and the wallet balance without spending anything. clean_product_data is free — it works on rows you already have and fetches nothing. A read-only key (LLM_READ) lists only the free tools — get_results, clean_product_data and the two read tools; the paid tools and building need a full-access key (LLM_FULL).

Setup tools (listed with ?toolsets=admin or ?toolsets=outcome,admin)

Build a scraper

scrapewise_preview_scraper_from_url · scrapewise_preview_scraper_from_curl · scrapewise_preview_scraper_preview_rule · scrapewise_create_scraper · scrapewise_create_scraper_v2 · scrapewise_create_file_scraper · scrapewise_get_scraper · scrapewise_get_scraper_v2 · scrapewise_get_scraper_list · scrapewise_get_scraper_config_parameters · scrapewise_update_scraper_schema · scrapewise_update_scraper_fallback · scrapewise_update_file_scraper_file · scrapewise_delete_scraper · scrapewise_delete_scraper_preview

Organise scrapers and their URLs

scrapewise_create_scraper_group · scrapewise_get_scraper_group_list · scrapewise_delete_scraper_group · scrapewise_delete_scraper_group_preview · scrapewise_create_scraper_site · scrapewise_get_scraper_site · scrapewise_get_scraper_site_links · scrapewise_update_scraper_site_from_source · scrapewise_delete_scraper_site · scrapewise_get_scraper_sitemaps · scrapewise_get_scraper_shared_group_list · scrapewise_list_scraper_shared_group_list · scrapewise_update_scraper_shared_group

Run

scrapewise_run_scraper · scrapewise_run_scraper_group · scrapewise_run_scraper_url_list · scrapewise_run_scraper_data_group · scrapewise_run_scraper_sitemaps_harvest · scrapewise_stop_scraper · scrapewise_stop_scraper_group · scrapewise_stop_scraper_shared_group · scrapewise_get_scraper_load_history · scrapewise_get_scraper_job_errors · scrapewise_get_scraper_load_site · scrapewise_get_scraper_load_site_content

Read the data

scrapewise_get_scraper_sample_data · scrapewise_get_scraper_data_group · scrapewise_get_scraper_data_group_client · scrapewise_get_scraper_data_group_categories · scrapewise_update_scraper_data_group_category · scrapewise_delete_scraper_data_group_category · scrapewise_delete_scraper_data_group_category_preview · scrapewise_get_run_columns · scrapewise_get_run_columns_batch · scrapewise_export_scraper_data_group · scrapewise_delete_scraper_data · scrapewise_delete_scraper_data_preview

Clean and convert

scrapewise_get_scraper_group_post_process_rules · scrapewise_update_scraper_group_post_process_rules · scrapewise_update_scraper_group_currency · scrapewise_update_scraper_group_ai_control · scrapewise_update_scraper_group_data_quality · scrapewise_create_customer_schema · scrapewise_list_customer_schema · scrapewise_delete_customer_schema · scrapewise_delete_customer_schema_preview

Monitor prices

scrapewise_update_scraper_group_price_monitor · scrapewise_get_scraper_group_price_monitor_anchor_competitors · scrapewise_update_scraper_group_price_monitor_anchor_competitor · scrapewise_delete_scraper_group_price_monitor_anchor_competitor · scrapewise_list_scraper_group_price_monitor_picks · scrapewise_update_scraper_group_price_monitor_pick · scrapewise_delete_scraper_group_price_monitor_pick

Schedule and retain

scrapewise_update_scraper_group_schedule · scrapewise_update_scraper_group_start_type · scrapewise_update_scraper_group_retention · scrapewise_update_scraper_retention

Enrichment and SEO fields

scrapewise_get_enrichment · scrapewise_delete_enrichment · scrapewise_list_enrichable_scrapers · scrapewise_get_scraper_seo_fields · scrapewise_search_scraper_seo_fields

Account

scrapewise_create_api_key · scrapewise_list_api_keys · scrapewise_delete_api_key

Manifest

server.json is a mirror. The authority is https://scrapewise.ai/server.json, which is served from the ScrapeWise site repo and checked by its test suite. If the two ever disagree, the hosted one is right.

Namespace ownership for ai.scrapewise/* is proved by the Ed25519 public key published at https://scrapewise.ai/.well-known/mcp-registry-auth.

Support

• Docs: docs.scrapewise.ai
• Email: siim.brazier@scrapewise.ai

Licence

MIT — see LICENSE. Covers this repository's contents only, not the hosted service.