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 Claude
Claude connects to a remote MCP server as a custom connector. The connection is made from Anthropic's cloud, not from your laptop, so the server must be on the public internet. Page Fetch is. These steps were checked against Claude's custom-connector article (updated 2026-08-11) and the Claude Code MCP docs on 2026-10-01.
On a Pro or Max plan:
- Open Customize, then Connectors.
- Select the plus button, then Add custom connector.
- Paste
https://pagefetch.openkrill.app/mcp. Leave Advanced settings empty: this server does not need an OAuth client id or secret. - Select Add. The connector is yours. Anthropic has not reviewed it, and it is not a Directory listing.
- In a conversation, open the plus button, then Connectors, and enable Page Fetch. Ask: Read https://example.com as Markdown.
On Team and Enterprise, an Owner adds the connector first at Organization settings, then Connectors, then Add, then Custom, then Web, and pastes the same URL. Members then connect it from Customize. A Free plan can add one custom connector.
In Claude Code, add it from the project directory:
claude mcp add --transport http page-fetch https://pagefetch.openkrill.app/mcpThat writes a local or user config. A JSON entry needs "type": "http" (or streamable-http) plus the url. An entry with a url and no type is skipped. Confirm with claude mcp get page-fetch. The tools you should see are fetch_page.
If Claude tries to fetch https://pagefetch.openkrill.app/mcp from its code sandbox and reports HTTP 403, the block is Claude's sandbox network allowlist, not this server. The sandbox proxy answers 403 with x-deny-reason: host_not_allowed for every host outside the allowlist. Use the connector above instead: connector calls come from Anthropic's cloud and do not pass the sandbox proxy. To let the sandbox reach it as well, an Owner adds pagefetch.openkrill.app under Settings, then Capabilities, then Additional allowed domains.
Enable the connector only in conversations that need it. Claude can call the tools while you work, including during research, so turn off any tool you do not want invoked. Page Fetch does not write to your accounts. It still receives the arguments of each call. Read the privacy page before you paste anything that is not public.
If it does not work
The tool does not show up
In Claude, enable the connector in the conversation from the plus button, then Connectors. In Claude Code, run claude mcp list from the same directory you added it in, then start a new session: a running session does not load a new server.
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.
JSON entry has no type
Claude Code skips an entry in .mcp.json that has a url but no type. Add "type": "http" next to the url, or add the server with claude mcp add --transport http, which writes the type for you. The VS Code entry needs the same type field. Cursor and Pi read the url alone.
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 Claude?
In Claude, open Customize, then Connectors, choose Add custom connector and paste https://pagefetch.openkrill.app/mcp. In Claude Code, run claude mcp add --transport http page-fetch https://pagefetch.openkrill.app/mcp. No restart is needed for either.
Do I need an API key to run Page Fetch in Claude?
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 Claude?
Check that the connector URL ends in /mcp and that Advanced settings are empty. In Claude Code, run claude mcp get page-fetch; a JSON entry with a url but no type is skipped, so add type http.