MrScraper for Gemini CLI

MrScraper connects Gemini CLI to a hosted MCP server for retrieving public web pages as HTML, Markdown, or screenshots, Google discovery, and account usage. The extension also includes three skills and three commands that help the agent choose the right workflow and keep raw page content.

What this extension adds

• The hosted Streamable HTTP endpoint at https://mcp.mrscraper.com/mcp.
• OAuth 2.1 sign-in through Gemini CLI's MCP client, with dynamic client registration. This repository stores no credentials.
• Skills: mrscraper, mrscraper-fetch, and mrscraper-serp.
• Commands: /mrscraper:fetch, /mrscraper:search, and /mrscraper:status.
• GEMINI.md context that routes known URLs to scraperAPI and open-ended questions to webSearch.

Requirements

• Gemini CLI 0.63.0 or later.
• A MrScraper account.
• A local browser for the OAuth sign-in.
• Permission to access and process the target content.

Install

gemini extensions install https://github.com/mrscraper-com/mrscraper-gemini-cli-extension

Gemini CLI asks you to trust the extension and confirm the install. Restart any running Gemini CLI session, then run /extensions list to confirm that mrscraper is enabled.

Sign in

Start Gemini CLI and run:

/mcp auth mrscraper

Gemini CLI discovers MrScraper's authorization server, registers itself, and opens your browser. Approve access on the MrScraper consent page; Gemini CLI stores and refreshes the tokens in ~/.gemini/mcp-oauth-tokens.json. Run the same command again if the tokens expire. Never paste OAuth tokens or API keys into the chat.

/mcp list should then show mrscraper as connected with these tools:

Tool	Purpose
scraperAPI	Retrieve a known page as HTML, Markdown, a screenshot, or a combination.
webSearch	Discover public pages through Google.
status	Inspect subscription status, token usage, and remaining tokens.

The OAuth scopes are scrape:read (scraperAPI and webSearch) and account:read (status).

Try it

/mrscraper:fetch https://www.scrapethissite.com/pages/simple/ and list the five most populous countries

/mrscraper:search best open source web scraping libraries 2026

/mrscraper:status

Or ask in plain language, for example "Fetch https://example.com as Markdown and summarize it." Gemini CLI asks for approval before it runs MCP tools unless your settings allow them.

Retrieve-first routing

When a public URL is already known, the skills direct the agent to retrieve it with scraperAPI first and treat the raw response as the source of truth. The agent can then read, summarize, compare, or derive structured output locally without losing details. When no URL is known, webSearch finds candidate pages first.

API key fallback

Use OAuth whenever possible. If OAuth cannot complete, for example on a machine without a browser, create an API key, export it as MRSCRAPER_API_KEY, and add a user-level server with a bearer header:

gemini mcp add --scope user --transport http \
  --header "Authorization: Bearer $MRSCRAPER_API_KEY" \
  mrscraper https://mcp.mrscraper.com/mcp

A server in settings.json with the same name takes precedence over the extension's server, so the skills and commands keep working. An API key carries full account authority, and gemini mcp add writes the header to ~/.gemini/settings.json in plain text; never add it to a project's .gemini/settings.json that is committed.

Data and permissions

The extension sends MCP tool inputs, including target URLs and search queries, to MrScraper's hosted service. Page responses and tool results are then available to the agent for the requested task. Use it only with public or otherwise authorized content, and follow the target site's requirements.

Review MrScraper's MCP documentation, Privacy Policy, and Terms of Use before use.

Update or remove

gemini extensions update mrscraper
gemini extensions uninstall mrscraper

Support and security

• Product help: MrScraper MCP documentation
• Bugs and feature requests: GitHub Issues
• Account help: support@mrscraper.com
• Security reports: see SECURITY.md

Development

gemini-extension.json   manifest and MCP server
GEMINI.md               context loaded into every session
commands/mrscraper/     /mrscraper:fetch, /mrscraper:search, /mrscraper:status
skills/                 mrscraper, mrscraper-fetch, mrscraper-serp

Validate and test a local checkout:

gemini extensions validate .
gemini extensions link .

The skills are copied from the canonical MrScraper MCP skills. The Gemini CLI extension gallery indexes this repository through its gemini-cli-extension topic. Record user-visible changes in CHANGELOG.md.

License

MIT