Fetch Router

dev.fetchrouter/fetchrouter-mcpVersion 0.1.2

Verified web fetch for agents: detects blocks and empty JS pages, falls back, bills only on success.

Status

Responds380 msNov 14, 2026, 14:26 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:26 UTC
Latency: 380 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://fetchrouter.dev/mcpResponds380 msNov 14, 2026, 14:26 UTC

No sign-in

Claude Code

claude mcp add --transport http fetchrouter-mcp https://fetchrouter.dev/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: fetchrouter-mcp
Remote MCP server URL: https://fetchrouter.dev/mcp

Cursor

{
  "mcpServers": {
    "fetchrouter-mcp": {
      "url": "https://fetchrouter.dev/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"fetchrouter-mcp","type":"http","url":"https://fetchrouter.dev/mcp"}'

Streamable HTTP

npm: fetchrouter-mcp 0.1.2

Package only

npm (npx)

claude mcp add fetchrouter-mcp -- npx -y fetchrouter-mcp@0.1.2

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

2 tools

Tools of Fetch Router
	Description		Read-only	Idempotent	Open world
`domain_reliability`Pass rates per route (plain HTTP, browser, providers) for a domain over the last 30 days, from real verified fetches. Use it to choose mode/max_cost before fetching a hard site. Free, no key needed.	Pass rates per route (plain HTTP, browser, providers) for a domain over the last 30 days, from real verified fetches. Use it to choose mode/max_cost before fetching a hard site. Free, no key needed.	Not declared	Yes	Not declared	Yes
`fetch_page`Fetch a public URL and get its content only if it really loaded. Use it when a page comes back as a block page, CAPTCHA, login wall or empty JavaScript shell, or when you need to know the content is real. It checks the page, retries through other routes (including a headless browser) automatically, and bills only on success. Works without a key up to a free daily allowance; a free key (500 credits) lifts it. Returns markdown by default. If ok is false, the reason says why (e.g. blocked:cloudflare, http_404, expect_text_missing): don't retry the same URL with the same settings.	Fetch a public URL and get its content only if it really loaded. Use it when a page comes back as a block page, CAPTCHA, login wall or empty JavaScript shell, or when you need to know the content is real. It checks the page, retries through other routes (including a headless browser) automatically, and bills only on success. Works without a key up to a free daily allowance; a free key (500 credits) lifts it. Returns markdown by default. If ok is false, the reason says why (e.g. blocked:cloudflare, http_404, expect_text_missing): don't retry the same URL with the same settings.	Not declared	Yes	Not declared	Yes

Details

Registry status: Active
Published: Nov 9, 2026
Updated: Nov 9, 2026
Website: https://fetchrouter.dev/⁠ (opens in a new tab)
Repository: https://github.com/JonnoGit/fetchrouter-mcp⁠ (opens in a new tab)
Categories (suggested): Search and webSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing