Access Google Maps, LinkedIn, Instagram, TikTok, and X data through 45 MCP tools with optional demo mode.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by ScrapeField.
The ScrapeField MCP server gives AI agents access to data from Google Maps, LinkedIn, Instagram, TikTok, and X. It exposes 45 API endpoints as MCP tools, covering platform-specific resources rather than normalizing every response into one shared schema.
Available data includes Google Maps places, details, reviews, photos, and posts; LinkedIn profiles, companies, searches, posts, and jobs; Instagram profiles, posts, comments, and hashtags; TikTok profiles, videos, comments, and searches; and X profiles, posts, replies, and searches.
The repository contains the MCP setup, an agent skill, and TypeScript and Python examples. The API itself is hosted at ScrapeField’s service rather than implemented as a local scraper in this repository.
The remote MCP endpoint is available at https://scrapefield.com/mcp and uses streamable HTTP. Each API endpoint is exposed as a tool. A client sends an authorization header with a ScrapeField live key for real responses:
Requests can instead run in demo mode. Adding demo=true produces one fixed response in the endpoint’s normal data shape, does not require an account or key, and does not consume credits. The MCP setup also includes a sign_up tool that asks the user for an account by email when needed.
Configure the server by adding the remote URL and, for live use, an authorization header to an MCP client. Claude Code can register it with the claude mcp add command using the HTTP transport. Clients that read mcp.json can use an entry with type set to http, the MCP URL, and an Authorization header.
The ScrapeField MCP server does not require a local installation to use its hosted endpoint. The repository includes separate examples for Node.js and Python: the TypeScript example runs on Node 22.18 or later without packages, while the Python example uses requests. Both provide demo and live variants; the live examples read the key from SCRAPEFIELD_KEY.
Live requests require a ScrapeField account and key. Demo responses are fixed examples, so they are suitable for checking tool wiring and response shapes rather than retrieving current platform data.
The service handles blocks without requiring users to rotate proxies, solve CAPTCHAs, or run a browser, according to the project documentation. The repository does not describe the MCP tools as a replacement for unrestricted or normalized access to the underlying platforms; each platform retains its own documented shape and endpoint set.
The skill can be copied into .claude/skills/ for Claude Code or saved as a rule in .cursor/rules/ for Cursor. The repository and examples are licensed under MIT.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/scrapefield)<a href="https://allmcps.com/mcp/scrapefield"><img src="https://allmcps.com/api/badge/scrapefield?style=directory" alt="ScrapeField on AllMCPs" /></a>