What can you do with fetcher?

fetcher.cloud — the web capability layer for AI agents

One MCP server and API that gives an autonomous AI agent the public web. Render and screenshot pages, extract clean content, resolve links, parse feeds, and inspect domains, DNS, SSL, and WHOIS — 18 capabilities, paid per-call in USDC via x402, with a free daily tier.

Whenever an agent needs something from the internet, it uses fetcher.

Why it exists

LLMs are brilliant at reasoning and blind at retrieval. The moment real-world data needs a browser, a payment, or a login, an agent stalls. fetcher is the specialist capability layer it calls — a single interface for everything an agent can't do alone, billed the only way that works for software: per call, in stablecoins, with no account or API key.

How agents use it

Discover — GET /capabilities returns every capability with category, pricing, examples, and schemas. Or connect the MCP server at /mcp.
Call — a normal GET request. The first unpaid call past the free tier returns 402 Payment Required with machine-readable terms.
Pay — the agent's wallet pays a fraction of a cent in USDC on Base and retries. No human in the loop.

Works with Conway Automaton, Claude, OpenAI Agents, Google ADK, any MCP client, or any agent that can make an HTTP request.

The capabilities

Category	Capabilities
Browser & rendering	`render`, `screenshot`
Content & extraction	`extract`, `unfurl`, `feed`, `oembed`, `pdf-text`, `diff`
Web intelligence	`resolve`, `headers`, `robots`, `favicon`
Domain & DNS	`domain`, `domain/enriched`, `whois`, `dns`, `ssl`
Utility	`qr`

Full catalog with pricing and examples: https://api.fetcher.cloud/capabilities

Machine-readable surfaces

/ (manifest) · /capabilities · /pricing.json · /openapi.json · /mcp · /.well-known/ai-plugin.json · llms.txt

Repository layout

worker/         # the Cloudflare Worker (API, payments, MCP)   → see worker/README.md
website/        # the landing page (Cloudflare Pages)
test-client/    # a script that pays an endpoint on Base mainnet
conway-skill/   # ready-to-submit Conway Automaton skill

Deploy

See worker/README.md and DEPLOY.md for step-by-step deployment (Cloudflare Workers + Pages). Payments require Coinbase CDP facilitator keys set as Worker secrets.

License

MIT — see LICENSE.

Install

Add fetcher to your client. Pick the one you use.

claude mcp add --transport http fetcher https://api.fetcher.cloud/mcp

codex mcp add fetcher --url https://api.fetcher.cloud/mcp

{
  "mcpServers": {
    "fetcher": {
      "url": "https://api.fetcher.cloud/mcp"
    }
  }
}

Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.

{
  "servers": {
    "fetcher": {
      "type": "http",
      "url": "https://api.fetcher.cloud/mcp"
    }
  }
}

Add to `.vscode/mcp.json` in your workspace.

{
  "mcpServers": {
    "fetcher": {
      "url": "https://api.fetcher.cloud/mcp"
    }
  }
}

Add to `claude_desktop_config.json`, then restart Claude Desktop.

{
  "mcpServers": {
    "fetcher": {
      "serverUrl": "https://api.fetcher.cloud/mcp"
    }
  }
}

Add to `~/.codeium/windsurf/mcp_config.json`.

Score

39 / 100

Incomplete

Documentation17/25
Maintenance25/25
Trust13/20
Capability0/15
Install experience12/15

Documents what it does and how to connect
Has a resolvable package or endpoint
Exposes at least one tool, prompt or resource
README has substantive content
Includes a code example
Documents its configuration
Mentions credentials or security posture
Last commit 3 days ago
Has a release history
Repository is not archived
Licensed MIT
Namespace verified in the official MCP registry
Claimed by its owner
Published under an organisation
0 tool(s) documented
Provides prompt templates
Provides resources
6 documented install method(s)
Published to a package registry
Offers a hosted endpoint — no local install

Read the full rubric →

Version history

Versions	Published
1.1.3Latest	Aug 4, 2026
1.1.2	Jul 29, 2026
1.1.1	Jul 29, 2026
1.1.0	Jul 29, 2026
1.0.1	Jul 28, 2026
1.0.0	Jul 28, 2026