MCP Server

Give Claude, ChatGPT, Cursor and Claude Code access to ScrapeReviews through the Model Context Protocol.

Connect from Claude.ai or ChatGPT (no install)

Add ScrapeReviews as a custom connector with this URL, then sign in with your ScrapeReviews account and allow access. It works on the web, desktop and mobile apps of the same account, with no API key to copy and nothing to install.

https://api.scrapereviews.com/mcp

Calls use your credits exactly like the API: reviews cost 1 credit per 5 reviews returned (min 1), a company profile 2 credits, search and category lists 1 credit per 10 results (min 1); failed calls are free. See or disconnect your connected apps in Dashboard → Connected apps.

Claude (claude.ai, Desktop, mobile)

  1. Open Customize → Connectors.
  2. Click + Add, then Add custom connector.
  3. Name it ScrapeReviews, paste the URL above as the remote MCP server URL, click Continue.
  4. Keep the authentication settings Claude detects (OAuth sign-in) and click Add.
  5. Sign in with your ScrapeReviews account and click Allow.
  6. In a chat, open + → Connectors and turn ScrapeReviews on.

The Free plan allows one custom connector. On Team and Enterprise an owner adds it in Organization settings → Connectors, then each member connects their own account.

ChatGPT

  1. Open chatgpt.com/plugins on the web.
  2. Click the plus button, then Add custom MCP server.
  3. Name it ScrapeReviews and paste the URL above as the Server URL under Connection.
  4. Choose OAuth as authentication, confirm I understand and want to continue, then Create as a plugin.
  5. Install it, sign in with your ScrapeReviews account and click Allow.
  6. In a new chat, type @ and pick ScrapeReviews.

Your account or workspace must allow custom MCP servers; workspace admins can restrict them.

Any MCP client that supports remote servers with OAuth (Streamable HTTP) can use the same URL, for example claude mcp add --transport http scrapereviews https://api.scrapereviews.com/mcp in Claude Code.

What is MCP?

The Model Context Protocol (MCP) lets AI assistants call external tools. With the ScrapeReviews MCP server, your assistant can search companies, read their profile and analyse their Trustpilot reviews on its own. Calls are billed like any API call, with your credits.

Local server with an API key (for developers)

Prefer to run the server on your machine? Same tools as the connector. Run it with uvx scrapereviews-mcp (Python, from PyPI) or npx -y scrapereviews-mcp (Node, from npm). Pass your API key in the SCRAPEREVIEWS_API_KEY environment variable.

// claude_desktop_config.json
{
  "mcpServers": {
    "scrapereviews": {
      "command": "uvx",
      "args": [
        "scrapereviews-mcp"
      ],
      "env": {
        "SCRAPEREVIEWS_API_KEY": "sr_your_api_key"
      }
    }
  }
}

Restart the assistant after editing its configuration. Create the key in Dashboard > API Keys.

Available tools

One tool per API endpoint, with the same parameters and the same credit cost:

search_companiesFind companies by name or domain
get_companyCompany profile: TrustScore, star distribution, languages, reply behavior, contacts
get_reviewsReviews with filters (stars, language, dates, verified, with reply, text search, sort)
list_categoriesThe category tree with ids
get_category_companiesCompanies of a category in a country, with TrustScore filter and sort

How it works

The connector runs on our API at https://api.scrapereviews.com/mcp and acts as the account you signed in with; the local server runs on your machine, talks to your assistant over stdio and uses your API key. When the assistant decides it needs Trustpilot data, it calls one of the tools above; the server turns the call into a request to the ScrapeReviews API and returns compact JSON (empty fields and logos are dropped to save context), always with the credits the call used.

Besides the tools, the server exposes documentation resources (the API reference, a quickstart, the pricing and workflow examples) and ready-made prompt templates to analyse the reviews of a company, compare companies and find the best companies of a category, so the assistant knows how to use the data without extra instructions.

Billing is the same as the REST API: reviews cost 1 credit per 5 reviews returned (min 1), a company profile 2 credits, and errors cost nothing. Each endpoint has its own page in the API reference.

Example prompts

“What is the TrustScore of monzo.com and how is it split across star ratings?”

“Summarize the 1-star reviews of www.monzo.com from the last month: what are the top 3 complaints?”

“Compare the TrustScores of the 10 most reviewed banks in the UK.”

“Find the Italian reviews of zalando.it that mention "reso" and check whether the company replied.”

“Which categories exist under "Animals & Pets"?”

Reading many reviews costs credits (1 credit per 5 reviews returned (min 1)): ask for a date range or star filter when you only need a sample.

Next Steps