How do I install master-fetch?

Its own README gives this command: pip install hound-mcp[all] && playwright install chromium. Run it where your MCP client can launch the server, and check the README for any settings it asks for.

What does master-fetch connect to, and what does it need?

It reaches another. The credentials we found in its source are ANOTHER_SERPER_KEY.

Is master-fetch official and is it maintained?

We found nothing naming it as a vendor’s official server. Its repository has 888 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-07-24.

What licence does master-fetch use?

The repository declares the MIT licence.

InfratoApp / Resources / MCP servers / master-fetch

master-fetch

master-fetch is an MCP server. It reaches another. It needs ANOTHER_SERPER_KEY to authenticate. Its repository has 888 GitHub stars and is licensed under MIT; we last read it on 2026-10-22.

Master-fetch fetches web content, bypasses Cloudflare, extracts text using Trafilatura, and routes requests intelligently. No API keys required.

Install

Read from master-fetch’s own README, close to verbatim -- not written by us, and not guessed.

pip install hound-mcp[all] && playwright install chromium

View in master-fetch’s own README ↗

What it reaches, and what it needs

Reaches

another

Credential

ANOTHER_SERPER_KEY

Maintenance

Stars

888

State

listed

Licence

MIT

From the repository

MCP server for web fetching with Cloudflare bypass, Trafilatura extraction, and smart routing. Free, self-hosted, no API keys.

View on GitHub ↗2026-10-22

What master-fetch can do

6 tools documented in its README. An AI client calls these by name.

smart_fetch: Fetch any URL. HTTP first, auto-escalates to the anti-detect browser if blocked. Bulk, PDFs (with OCR + quality score), `css_selector`, `focus`, `actions`, pagination.
smart_crawl: Best-first same-domain crawl. Each page as markdown with `content_ok` + `page_type` (article / list / js_shell). `discover_only`, `crawl_urls`, `focus`, sitemap mode, time + token caps.
smart_search: Local keyless web search. 10 backends in parallel, merges + ranks with neural rerank + cross-backend consensus. `relevance_score` + `engines_consensus` per result.
screenshot: Capture a page as an image. For multimodal agents (canvas, image-of-text, visual layout).
cache_clear: Clear the fetch cache. `all=true` wipes everything.
version: Installed version + update status.

Read from the README; names are kept only if the README contains them.

Common questions about master-fetch

What does master-fetch do?: Master-fetch fetches web content, bypasses Cloudflare, extracts text using Trafilatura, and routes requests intelligently. No API keys required.
How do I install master-fetch?: Its own README gives this command: pip install hound-mcp[all] && playwright install chromium. Run it where your MCP client can launch the server, and check the README for any settings it asks for.
What does master-fetch connect to, and what does it need?: It reaches another. The credentials we found in its source are ANOTHER_SERPER_KEY.
Is master-fetch official and is it maintained?: We found nothing naming it as a vendor’s official server. Its repository has 888 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-07-24.
What licence does master-fetch use?: The repository declares the MIT licence.