Skip to content
Skills Library
Data & analytics · Conversion & formats

agentfetch

/agentfetch

Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the AgentFetch API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.

Repository
cli ↗
Licence
MIT
Last repository change
13.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
8
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the AgentFetch API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.

Original author description

Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the AgentFetch API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.

How it works

  1. With the MCP server
  2. With the CLI
  3. Rules
Original SKILL.md headings · 34 lines, 233 words
SKILL.md preview
---
name: agentfetch
description: Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the AgentFetch API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.
---

# AgentFetch: live web pages as Markdown

Use this when the user gives you a URL, or you found one, and you need the page's current content. It does not search
the web, log in or submit forms.

## With the MCP server

If the `agentfetch` MCP server is connected (`https://agentfetch.live/mcp`), call its tools:

- `get_page_contents`: one URL in, the page's main content out.
- `get_account_status`: remaining credits, plan and rate limit. Check it before a large batch.

## With the CLI

No MCP server? Use the `agentfetch` command (Node.js 18 or later). It needs the key in `AGENTFETCH_API_KEY`, or
saved once with `npx @agentfetch-live/cli login`.

```bash
npx @agentfetch-live/cli fetch https://example.com -o text                    # Markdown, else text, else HTML
npx @agentfetch-live/cli fetch https://example.com/a https://example.com/b    # up to 10 URLs, JSON with results[] and statuses[]
npx @agentfetch-live/cli fetch https://example.com --render                   # rendered in a real browser
npx @agentfetch-live/cli fetch https://example.com --country-code de          # from another country
npx @agentfetch-live/cli account                                              # plan, credits and rate limit
npx @agentfetch-live/cli fetch --help                                         # every option
```

## Rules

- Each fetched URL costs credits; do not fetch the same URL twice in one task.
- Exit code 1 means the API answered with an error (JSON on stderr), 2 a usage error, 3 no network answer.
- No key yet: tell the user to get one at https://agentfetch.live. Never print or log the key.
- Docs: https://agentfetch.live/docs

Versions

The database has no other skills named agentfetch.

Database snapshot: 13.11.2026 · package version 3cce8b49e233 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100siterender
    Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the SiteRender API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.
  • 100agentscraper
    Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the AgentScraper API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.
  • 100livewebdata
    Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the Live Web Data API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.
  • 100contextretrieval
    Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the Context Retrieval API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.
  • 100fetchmcp
    Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the FetchMCP API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.
  • 100mcpscraper
    Fetch a public web page live and get its main content as clean Markdown, plain text or HTML, through the MCPScraper API. Use when you have a specific URL and need what the page says now, for example docs, articles, product or listing pages, including pages that need a real browser to render.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.