Koskamo

ScrapeField MCP

An official MCP server provided by ScrapeField that exposes 45 tools for AI agents to scrape data from Google Maps, LinkedIn, Instagram, TikTok, and X. It supports tasks like searching places, retrieving profiles, and analyzing social media content, with a demo mode available for evaluation without an API key.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

ScrapeField MCP logo, by ScrapeFieldNo sign-inEndpoint checked 2026-10-19Operated by ScrapeField
MCP endpoint (Streamable HTTP)
https://scrapefield.com/mcp
Vendor documentation

What you can do with it

  • Search Google Maps for businesses and places
  • Retrieve LinkedIn company profiles and employee stats
  • Get Instagram posts and comments for specific accounts
  • Search TikTok videos and trending content
Tools advertised by the last live check:
  • search_places
  • get_place
  • get_place_reviews
  • get_place_photos
  • get_place_posts
  • get_linkedin_profile
  • get_linkedin_company
  • get_linkedin_employee_stats
  • get_linkedin_company_people
  • search_linkedin_people
  • search_linkedin_services
  • search_linkedin_companies
  • get_linkedin_posts
  • get_linkedin_post
  • get_linkedin_post_comments
  • get_linkedin_post_reactions
  • get_linkedin_activity
  • search_linkedin_jobs
  • get_linkedin_job
  • search_linkedin_ads
  • get_linkedin_ad
  • get_linkedin_group
  • search_linkedin_groups
  • get_instagram_profile
  • get_instagram_posts
  • get_instagram_post
  • get_instagram_comments
  • get_instagram_hashtag
  • search_instagram_accounts
  • get_tiktok_profile
  • get_tiktok_followers
  • get_tiktok_videos
  • get_tiktok_video
  • get_tiktok_comments
  • search_tiktok
  • get_tiktok_trending
  • search_tiktok_ads
  • get_x_profile
  • get_x_posts
  • get_x_post
  • get_x_replies
  • get_x_retweeters
  • get_x_followers
  • search_x
  • get_x_community
  • sign_up
  • check_sign_up

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http scrapefield-mcp https://scrapefield.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add scrapefield-mcp --url https://scrapefield.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable scrapefield-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "scrapefield-mcp": {
      "url": "https://scrapefield.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.
Cline configuration
{
  "mcpServers": {
    "scrapefield-mcp": {
      "type": "streamableHttp",
      "url": "https://scrapefield.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start scrapefield-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "scrapefield-mcp": {
      "type": "http",
      "url": "https://scrapefield.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http scrapefield-mcp https://scrapefield.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "scrapefield-mcp": {
      "url": "https://scrapefield.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "scrapefield-mcp": {
      "serverUrl": "https://scrapefield.com/mcp"
    }
  }
}

Ground your agent in cited data

ScrapeField MCP gives your agent tools. Koskamo gives it reviewed, cited facts to check its answers against. Add it as a second MCP server; public reads need no API key.

Do you run ScrapeField MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing