Claude MarketplacesSubmit

Intercept

bighippoman/intercept-mcp

Exposes fetch and search tools that convert web pages to clean markdown using a 15-strategy fallback pipeline. Handles site-specific formats like tweets, YouTube transcripts, arXiv papers, PDFs, and GitHub READMEs before falling back to Jina Reader, archive services, and stealth fetching. Routes requests through agentsweb.org's shared cache first for sub-50ms hits on previously fetched URLs. No API keys required for basic fetching, though you'll want Brave or SearXNG for reliable search and Cloudflare Browser Run for JavaScript-heavy sites. Includes research-topic and extract-article prompts that chain search with multi-source fetching. Reach for this when you need to give Claude reliable web access without hitting 403s or wrestling with raw HTML.

GitHub stars: 7
tools: 5
auth: Secret needed
transport: STDIO
env var: 1
last updated: Mar 4, 2026

Tools

5 tools

Public tool metadata for what this MCP can expose to an agent.

fetchFetch a URL and return its content as clean markdown.

Fetch a URL and return its content as clean markdown.

No parameter schema in public metadata yet.

fetch_batchFetch up to 10 URLs in parallel, each through the same handler/fallback chain.

Fetch up to 10 URLs in parallel, each through the same handler/fallback chain.

No parameter schema in public metadata yet.

researchSearch the web and fetch the top results in one call — replaces a search followed by several fetches.

Search the web and fetch the top results in one call — replaces a search followed by several fetches.

No parameter schema in public metadata yet.

searchSearch the web and return results.

Search the web and return results.

No parameter schema in public metadata yet.

extractExtract specific values from a page as JSON instead of markdown prose — for when you need particular data, not the whole page.

Extract specific values from a page as JSON instead of markdown prose — for when you need particular data, not the whole page.

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Configuration

BRAVE_API_KEYsecret

Brave Search API key for the search tool (free tier: 2,000 queries/month). Not needed for the fetch tool.

Readme

intercept-mcp

Give your AI the ability to read the web. One command, no API keys required.

Without it, your AI hits a URL and gets a 403, a wall, or a wall of raw HTML. With intercept, it almost always gets the content — clean markdown, ready to use.

Handles tweets, YouTube videos (with transcripts when available), arXiv papers, PDFs, Wikipedia articles, and GitHub repos. If the first strategy fails, it tries up to 14 more before giving up.

Works with any MCP client: Claude Code, Claude Desktop, Codex, Cursor, Windsurf, Cline, and more.

intercept-mcp MCP server

Install

Claude Code

claude mcp add intercept -s user -- npx -y intercept-mcp

Codex

codex mcp add intercept -- npx -y intercept-mcp

Cursor

Settings → MCP → Add Server:

{
  "mcpServers": {
    "intercept": {
      "command": "npx",
      "args": ["-y", "intercept-mcp"]
    }
  }
}

Windsurf

Settings → MCP → Add Server → same JSON config as above.

Claude Desktop

View the full README on GitHub

Details

Repository: github.com/bighippoman/intercept-mcp
Category: Documents & Knowledge
Package: intercept-mcp
Transport: STDIO
Auth: Required
Registry: MCP registry, active

More from bighippoman

Related Documents & Knowledge MCP servers

1

Scribocausa-prima-ai/scribo-mcpEN 16931-compliant e-invoices: XRechnung, ZUGFeRD, Factur-X, Peppol BIS, Facturae or US PDF. Free.7stars

2

MINDtheastraway/mind-mcp-serverMIND knowledge-graph memory for agents. 44 tools: CRM, Life, MoneyMIND, Budget, Sheets, Email, Sign.7stars

3

Octocrawl77777r7/octocrawlPages, crawls and URL batches as clean Markdown and JSON for AI agents, with an Evidence Record.6stars

4

Aspiciofrontsail-ai/aspicioDXF and PDF/X-4 for AI agents: structured facts, PNG renders, an interactive in-chat viewer.6stars

5

Crawlforge Mcp Servermysleekdesigns/crawlforge-mcpWeb scraping, crawling, deep research & autonomous extraction — 31 MCP tools, clean Markdown/JSON6stars

6

RAGMapkhalidsaidi/ragmapFind a retrieval MCP server that works today: a daily-checked list of servers that search knowledge.6stars