Skip to main content
Glama
Sign In
cleanfetch

cleanfetch

by belzorash
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

cleanfetch

An MCP server that gives AI agents clean, reliable web reading. One job, done well.

Tool

Input

Output

fetch_clean

a URL

the page's main content as clean Markdown + title/byline (nav/ads/scripts stripped)

extract_links

a URL

all hyperlinks with anchor text, classified internal/external

extract_metadata

a URL

title, description, canonical, robots, Open Graph, JSON-LD, headings outline

Why this exists

Agent builders constantly need to read web pages — but the generic fetchers choke on real-world HTML, return nav/ad noise, or get blocked. Reliability is the moat: a server that consistently returns clean, structured content is worth paying for. There are 14,000+ MCP servers listed and almost none are production-hardened or monetized — that's the opening.

Related MCP server: Onto MCP Server

Run it locally

npm install
npm run build
npm start          # runs on stdio
# or, no build step:
npm run dev

Sanity-check the tools with the MCP Inspector:

npm run inspect

Connect it to a client

Claude Desktop / Claude Code / Cursor — add to the MCP config:

{
  "mcpServers": {
    "cleanfetch": {
      "command": "node",
      "args": ["/Users/alexandre/projects/mcp-cleanfetch/dist/index.js"]
    }
  }
}

Then ask the agent: "Use fetch_clean to read https://example.com and summarize it."

Config (env vars)

  • CLEANFETCH_UA — override the User-Agent.

  • CLEANFETCH_TIMEOUT_MS — request timeout (default 15000).

Go-to-market (the actual point)

1. List it everywhere (free distribution). Submit to the MCP directories — this is the "App Store moment", and free-tier listings rank highest:

Publish to npm so npx mcp-cleanfetch works, and add a 30-second demo GIF to the README.

2. Harden the moat (what makes it paid-worthy). Roadmap, in order of value:

  • JS rendering fallback (Playwright) for client-side-rendered pages.

  • Rotating proxies + retry/anti-bot handling for sites that block plain fetch.

  • Caching + rate limiting.

  • batch_fetch (many URLs in one call), search (query → top results → clean content).

3. Monetize. Free tier = local stdio (what's here). Paid tier = a hosted HTTP MCP endpoint with an API key + usage billing:

  • Host the server over the Streamable HTTP transport (the SDK supports it).

  • Meter calls per key; bill with Stripe (Stripe shipped MCP/usage billing rails in 2026) or a usage-billing layer. Typical pricing in this category: a free tier + ~$20–40/mo, or per-call credits. Realistic target: $0.5–3K MRR per server — cheap enough to run several.

4. Validate before hardening. Ship the free version, list it, and watch installs/usage. If a tool gets real pull, that's the signal to build the paid hosted tier. Don't build billing for a server nobody installs.

License

MIT

Available Tools

3 tools
extract_linksExtract links from a pageA

Fetch a page and return all hyperlinks with their anchor text, each classified as internal or external. Useful for crawling and agent navigation.

Inputs: url (required), limit, internalOnly.

extract_metadataExtract structured metadataA

Fetch a page and return structured metadata: title, description, canonical URL, robots, Open Graph tags, JSON-LD blocks, and a headings outline. Lets an agent analyze a page's structure without reading the whole body.

Inputs: url (required).

fetch_cleanFetch page as clean MarkdownA

Fetch a web page and return its main article content as clean Markdown plus core metadata (title, byline). Strips navigation, ads, and scripts so an agent can read the page reliably.

Inputs: url (required), maxChars.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.2/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool targets a distinct aspect of web page analysis: links, metadata, and clean content. There is no functional overlap between extract_links, extract_metadata, and fetch_clean.

    Naming Consistency4/5

    Tools follow a verb_noun pattern, but fetch_clean uses 'fetch' while the other two use 'extract'. This is a minor inconsistency but still clear and predictable.

    Tool Count5/5

    Three tools is a well-scoped set for a clean fetching utility, covering the essential operations without unnecessary complexity.

    Completeness5/5

    The tools cover all key aspects of web page extraction: links, metadata, and clean content. No obvious gaps for the stated purpose of agent navigation and analysis.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers