Koskamo

MCP Web Reader

A public Model Context Protocol server that fetches any public web page and returns its main content as clean Markdown, metadata, and outbound links. It uses deterministic extraction (Mozilla Readability + Turndown) without LLMs, ensuring SSRF safety by blocking private addresses. It supports tools for fetching markdown, searching page passages, retrieving metadata, and extracting links, enabling AI agents to access live web content efficiently.

Visit Vanshul

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

MCP Web Reader logo, by VanshulCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Vanshul
MCP endpoint (Streamable HTTP)
https://mcp.vanshul.com/mcp
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (4)

4 of 4 have a description · 0 of 4 declare behavior hints · 4 of 4 with parameters document them all

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

  • Give AI agents live web access to read current articles or docs
  • Research and summarization by pulling clean Markdown without boilerplate
  • Pinpoint specific details using relevance-ranked passage search
  • Lightweight crawling by extracting and following outbound links

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.vanshulgoyal101/mcp@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
vanshul-web-reader 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Tools to read the live web as clean Markdown. Pass an absolute http(s) URL.

Tools

4 advertised

fetch_markdown
Advertised by the server during the last successful anonymous check.

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_markdown input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The absolute http(s) URL of the page."
    },
    "max_chars": {
      "type": "number",
      "description": "Optional. Truncate the Markdown to at most this many characters to fit a context budget."
    }
  }
}
fetch_metadata
Advertised by the server during the last successful anonymous check.

Fetch a web page and return its metadata as JSON: title, byline, site name, excerpt and word count (no full body).

fetch_metadata input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The absolute http(s) URL of the page."
    }
  }
}
extract_links
Advertised by the server during the last successful anonymous check.

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.

extract_links input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The absolute http(s) URL of the page."
    },
    "limit": {
      "type": "number",
      "description": "Max links to return (default 200)."
    }
  }
}
search_page
Advertised by the server during the last successful anonymous check.

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_markdown.

search_page input schema
{
  "type": "object",
  "required": [
    "url",
    "query"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The absolute http(s) URL of the page."
    },
    "query": {
      "type": "string",
      "description": "Space-separated search terms; matching is case-insensitive."
    },
    "max_matches": {
      "type": "number",
      "description": "Max passages to return (1-50, default 5)."
    },
    "context_chars": {
      "type": "number",
      "description": "Per-passage character budget (50-4000, default 500)."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource 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
398 ms
95th percentile latency
398 ms

Maintenance history

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

  • · probe · passed · 398 ms · metadata changed · 4 tool(s)

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 mcp-web-reader https://mcp.vanshul.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 mcp-web-reader --url https://mcp.vanshul.com/mcp

Cursor

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

Cline

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

VS Code

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

Let your agent find its tools

Find servers like MCP Web Reader 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 8,296