io.github.vojtisprime11/web-fetcher
mcp-server-web-fetcher
Turns any web page into clean Markdown, page metadata and classified links for LLMs.
alive probed 2026-10-15
3tools
1.6ktokens in Claude Opus 5.5
1.6ktokens in Claude Code
0.8 %of a 200k context window
888o200k_base estimate
838 msto initialize
26 msto list tools
- Run it
- npx -y mcp-server-web-fetcher@0.1.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- mcp-server-web-fetcher 0.1.0
- Capabilities
- tools
- Instructions
- 587 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/vojtisprime11/mcp-server-web-fetcher
- Registry
- active, updated 2026-07-30 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| fetch_page_markdown | 365 | 41 % |
| extract_links | 275 | 31 % |
| extract_metadata | 248 | 28 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.vojtisprime11/web-fetcher)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.