mcpField
F
firecrawl-knowledge-ingest

firecrawl-knowledge-ingest

github.com/firecrawlData & databases1393.8k installsUpdated 6d ago
Repository

About firecrawl-knowledge-ingest

A skill for extracting documentation portals into structured knowledge content with Firecrawl browser. It handles navigation, authentication, pagination, and JavaScript-rendered pages while tracking extraction progress and failures.

Key features

  1. 01Navigate documentation portals
  2. 02Handle authentication and JavaScript-rendered pages
  3. 03Follow sections, pagination, and search
  4. 04Extract article content and metadata
  5. 05Track progress and page failures

Use cases

  1. 01Ingest paginated documentation
  2. 02Collect articles from authenticated portals
  3. 03Export documentation as JSON or Markdown

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/firecrawl/skills --skill firecrawl-knowledge-ingest

After installing, type/firecrawl-knowledge-ingestin Claude Code to confirm it loaded.

Details

From the project README

Firecrawl Knowledge Ingest

Use this when a docs portal needs browser navigation, auth, pagination, or JS rendering.

Onboarding Interview

Infer the portal URL, output format, auth needs, and page limit from context. If the portal is clear, proceed immediately.

Ask at most 1-3 concise questions only if blocked, such as the portal URL, whether authentication is required, or the desired output format.

Firecrawl Collection Plan

Use Firecrawl browser to:

  • open the portal and inspect navigation
  • identify sections, categories, sidebar links, and article URLs
  • follow sidebar navigation, next links, pagination, load-more controls, or search
  • scrape article content as markdown
  • extract metadata such as title, section, last updated date, author, and tags

Try Firecrawl map as a supplement for public URLs, but use browser navigation for auth-gated or JS-heavy content.

Final Deliverable

# Knowledge Ingest: [Portal]

## Summary
[Pages extracted, sections covered, limitations]

## Output
[JSON/markdown/merged file path or content]

## Sections
[Section names and article counts]

## Failed Or Restricted Pages
[Any access/loading issues]

## Sources
[URLs extracted]

## Rerun Inputs
workflow: firecrawl-knowledge-ingest
url: [portal url]
format: [json/markdown/merged]
max_pages: [number]

JSON Shape

Use source, url, extractedAt, totalArticles, and sections[] with article title, url, section, content, and metadata.

Quality Bar

  • Preserve code examples, tables, and formatting.
  • Strip nav chrome, headers, and footers.
  • Track extraction progress and page failures.
  • Respect authentication boundaries.

Comments

Markdown supported