MCP server with multi-tier fallback chain for fetching web content as clean markdown
Most search and retrieval work still happens through a UI a human drives. Intercept MCP MCP server moves it into the conversation instead. MCP server with multi-tier fallback chain for fetching web content as clean markdown.
Give your AI the ability to read the web. One command, no API keys required.
The server publishes 8 tools. What each one is for:
Codex — The Codex tool exposed by this serverCursor — The Cursor tool exposed by this serverWindsurf — The Windsurf tool exposed by this serverfetch — Long pages are truncated at maxLength with a notice telling the agent which startIndex continues the content. Structured output reports sourcefetch_batch — Fetch up to 10 URLs in parallel, each through the same handler/fallback chainresearch — Search the web and fetch the top results in one call — replaces a search followed by several fetchessearch — Uses Brave Search API if BRAVE_API_KEY is set, then SearXNG if SEARXNG_URL is set, then DuckDuckGo as an unreliable last resort. freshness and pageextract — Extract specific values from a page as JSON instead of markdown prose — for when you need particular data, not the whole page. Honors per-domain authConfiguration is passed through the environment: GITHUB_TOKEN, BRAVE_API_KEY, SEARXNG_URL, CF_API_TOKEN, CF_ACCOUNT_ID, FLARESOLVERR_URL, WEB_UNLOCKER_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
Plenty of search and retrieval servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Intercept MCP's toolset — Codex, Cursor, Windsurf and 5 more — is a fair guide to whether it matches your workflow. It is maintained by bighippoman; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Codex | The Codex tool exposed by this server. |
| Cursor | The Cursor tool exposed by this server. |
| Windsurf | The Windsurf tool exposed by this server. |
| fetch | Long pages are truncated at maxLength with a notice telling the agent which startIndex continues the content. Structured output reports source, quality, contentLength, truncated, nextStartIndex, and cacheAgeSeconds so ag |
| fetch_batch | Fetch up to 10 URLs in parallel, each through the same handler/fallback chain. |
| research | Search the web and fetch the top results in one call — replaces a search followed by several fetches. |
| search | Uses Brave Search API if BRAVE_API_KEY is set, then SearXNG if SEARXNG_URL is set, then DuckDuckGo as an unreliable last resort. freshness and page are ignored by the DuckDuckGo fallback. |
| extract | Extract specific values from a page as JSON instead of markdown prose — for when you need particular data, not the whole page. Honors per-domain auth and proxies. |
{
"mcpServers": {
"intercept": {
"command": "npx",
"args": ["-y", "intercept-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GITHUB_TOKEN | Credential the server authenticates with. | Yes |
| BRAVE_API_KEY | Credential the server authenticates with. | Yes |
| SEARXNG_URL | Endpoint or connection string the server talks to. | Yes |
| CF_API_TOKEN | Credential the server authenticates with. | Yes |
| CF_ACCOUNT_ID | Configuration value read at startup. | Optional |
| FLARESOLVERR_URL | Endpoint or connection string the server talks to. | Yes |
| WEB_UNLOCKER_URL | Endpoint or connection string the server talks to. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.