Questions it answers
Page Fetch reads one public web page and returns its main content as clean Markdown, with the page title, description, language, canonical address and a list of the links in the content.
It keeps headings, paragraphs, lists, quotes, code blocks, tables, emphasis and links, with every link made absolute. Menus, headers, footers, side columns, scripts, cookie banners and hidden text are left out, so an agent reads the page and not the site around it.
robots.txt is read before every page, and a page it disallows for PageFetch or for all crawlers is not read; the answer says why. Each site is read at most once a second (more when its robots.txt asks), at most 300 times a day, and a page read in the last 60 minutes is answered from the stored copy with no new request. The reader names itself as PageFetch/1.0 (+https://tools.openkrill.app/; support@openkrill.app).
It reads only public pages. It does not sign in, pass a paywall, solve a CAPTCHA or run page scripts, so a page built only by script comes back short with a note. PDFs and images are refused.
Each page's Markdown is kept for 60 minutes so a repeat call does not reach the site again, then deleted. Nothing about the caller is stored.
What it can do
- Turns one public web page into clean Markdown with absolute links
- Keeps headings, lists, quotes, code blocks and tables; drops menus, footers and banners
- Returns up to 100 distinct links from the main content, marked internal or external
- Checks robots.txt before every page and says why a page was not read
- Returns the title, description, language and canonical address of the page
Tools
fetch_page, Fetch a web page as Markdown. Read one public web page and return its main content as clean Markdown: headings, paragraphs, lists, quotes, code blocks, tables and absolute links, without menus, footers, scripts or cookie banners. Also returns the title, description, language, canonical address and up to 100 links from the content. robots.txt is checked first and a disallowed page is skipped with the reason. It never signs in, passes a paywall, solves a CAPTCHA or runs page scripts. Pass max_chars for more than 20000 characters.
Add Page Fetch in Pi
Pi does not speak MCP on its own. The pi-mcp-adapter extension (these steps match version 2.34.0) loads remote servers and keeps their schemas out of the prompt until you ask. Install it once, then restart Pi:
pi install npm:pi-mcp-adapterAdd the server to a shared MCP file. Use .mcp.json in the project if only that project needs Page Fetch, or ~/.config/mcp/mcp.json if you want it in every project. Pi also reads ~/.agents/mcp.json. A Pi-only override lives in ~/.pi/agent/mcp.json or .pi/mcp.json and wins over the shared file.
{
"mcpServers": {
"page-fetch": {
"url": "https://pagefetch.openkrill.app/mcp",
"lifecycle": "eager"
}
}
}The url is enough. Do not set command: that field is for a local process. No API key header. lifecycle is eager so Pi connects at startup and can search tool names before the first call. A config that omits it still works: the first call connects. After restart, run /mcp and confirm the server is listed. Ask: Read https://example.com as Markdown. The adapter should offer fetch_page.
Leave directTools off unless you want those schemas in every turn. With a handful of tools the cost is small. The default proxy is the better fit: search for the tool, then call it. /mcp disable page-fetch writes a project override in .pi/mcp.json without editing the shared file. Run /reload after that change.
Pi will not find this server by scanning Cursor or Claude config unless you run /mcp setup and import it. Putting the url in .mcp.json is the direct path and the one this page tests against. The server is the same public endpoint the other clients use, with the same limits and the same privacy rules.
If it does not work
The tool does not show up
Run /mcp to see the servers the adapter loaded. If it is missing, check the url entry in .mcp.json, then run /reload or restart Pi.
429 or rate_limited
Each server takes 60 calls a minute from one network, and some tools take fewer. Past that the call comes back as a tool error that starts with rate_limited: wait a minute and ask again. daily_limit means the server reached its shared daily cap, which resets at 00:00 UTC. A limit is not an answer, so do not read it as no results. For higher limits, ask support@openkrill.app for a key.
A call checked on 2026-10-11
RFC 9309 is the robots.txt standard, a public page whose text does not change, so the Markdown can be checked against it. The request below was posted to https://pagefetch.openkrill.app/mcp as tools/call. HTTP 200. Source: the Page Fetch server, read 2026-10-11.
{
"method": "tools/call",
"params": {
"name": "fetch_page",
"arguments": {
"url": "https://www.rfc-editor.org/rfc/rfc9309.html",
"max_chars": 3000
}
}
}- status. ok
- title. RFC 9309: Robots Exclusion Protocol
- url. https://www.rfc-editor.org/rfc/rfc9309.html
- links. 15 returned
Repeat the call yourself if you need a newer reading. Cached answers expire. A rate limit is not a result: wait and try again. Nothing in the call is a ranking, a filing, or advice.
Using it in production
Nothing to install and nothing to run: no package, no Python or Node.js version and no environment variable. Page Fetch runs on our servers, and your client only needs the URL https://pagefetch.openkrill.app/mcp.
| Rate limit | 60 tool calls a minute from one network. initialize and tools/list do not count. |
|---|---|
| Daily cap | 5000 tool calls a day per server, shared by every caller. It resets at 00:00 UTC. |
| At a limit | The call comes back as a tool error that starts with rate_limited (wait a minute) or daily_limit (try after 00:00 UTC), never as a partial answer. |
| Key | None. Do not add an Authorization header or a key field. |
| Higher limits | Email support@openkrill.app with the server name, the calls a day you expect and what they are for. We answer within 1 business day. |
| Freshness | Some answers come from a short cache. Each guide shows the date of its checked call; repeat a call when you need a newer reading. |
| Uptime | Scheduled test calls check the servers through the same endpoint. There is no SLA yet. |
| Data | What each server receives and keeps is on the privacy page. |
Use it in other apps
Frequently asked questions
How do I install the Page Fetch MCP server in Pi?
Run pi install npm:pi-mcp-adapter once, add page-fetch with the url https://pagefetch.openkrill.app/mcp to .mcp.json, then restart Pi and run /mcp to see it.
Do I need an API key to run Page Fetch in Pi?
No. This server takes no API key. For higher limits, email support@openkrill.app with the server name (Page Fetch), the calls a day you expect and what they are for. We answer within 1 business day.
What should I do if Page Fetch does not connect in Pi?
Check that the entry has a url and no command field, then run /reload or restart Pi and run /mcp.