Koskamo

Webcrawl MCP

Webcrawl MCP provides AI agents with live web data capabilities including search, scraping, mapping, and crawling. It returns clean, structured data from any site, even those blocking bots, and supports reading PDFs, Office files, images, and recordings via OCR and transcription.

Visit Brainfish

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

Webcrawl MCP logo, by BrainfishCommunity listingStreamable HTTPOAuth sign-inEndpoint checked 2026-11-07Published by Brainfish
You need:Add the URL https://webcrawl.app/mcp as an MCP server and sign in with your email when asked
MCP endpoint (Streamable HTTP)
https://webcrawl.app/mcp
Vendor documentation

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search the live web for ranked results with clean content
  • Scrape any URL as clean markdown or JSON
  • Map every URL on a site in one call
  • Crawl whole docs sites or catalogues for agent context

Source and maintenance

Community listingRegistry 1.4.3
mcp-registry: io.github.brainfish-ai/webcrawl@1.4.3Source repositoryProject website
Maintenance checked

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
634 ms
95th percentile latency
634 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 634 ms · metadata changed · refuses unauthenticated initialize (HTTP 401)

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 the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http webcrawl-mcp https://webcrawl.app/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 webcrawl-mcp --url https://webcrawl.app/mcp

Cursor

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

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "webcrawl-mcp": {
      "type": "streamableHttp",
      "url": "https://webcrawl.app/mcp",
      "disabled": false
    }
  }
}

VS Code

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

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://webcrawl.app/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": {
    "webcrawl-mcp": {
      "serverUrl": "https://webcrawl.app/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Webcrawl MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 8,848