MCP
by vanshul.com in Search & web
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.
https://mcp.vanshul.com/mcp
Last 30 days
- Uptime
- 100%
- Response time
- 182 ms typical, 182 ms slowest 5%
- Last check
- 7 h ago
- Next check
- any minute now
How to call it
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"mcp-267": {
"type": "http",
"url": "https://mcp.vanshul.com/mcp"
}
}
}4 tools
- fetch_markdown
Fetch a web page and return its main content as clean Markdown (nav, ads and boilerplate removed). Raw Markdown, plain-text and JSON endpoints are returned as-is. Use this to read an article, docs page or raw file.
- fetch_metadata
Fetch a web page and return its metadata as JSON: title, byline, site name, excerpt and word count (no full body).
- extract_links
Fetch a web page and return all of its outbound http(s) links (with anchor text) as JSON. Useful for crawling or finding related pages.
- search_page
Fetch a web page and return only the passages that match a query, instead of the whole page. Each result includes its heading breadcrumb and is ranked by relevance. Use this to find a specific detail (e.g. pricing, a config option) while spending far fewer tokens than fetch_markd
Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 7 h ago | Passed | 200 | 182 ms |