Fetch Router

dev.fetchrouter由 fetchrouter.dev 发布官方发布者v0.1.1更新于 Nov 3, 2026

面向智能体的经验证的网页抓取：检测拦截和空白JS页面，自动回退，仅在成功时计费。

AI 翻译由 AI 模型根据下方的原文描述翻译，可能有误。

原文描述

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

已验证Streamable HTTP可网页运行

概览

Fetch Router 的托管 MCP 服务（fetchrouter.dev），由 fetchrouter.dev 发布；需要 API 密钥；Streamable HTTP；2 个工具。

暂无 AI 概览：以下信息来自注册中心条目和服务本身。

发布者
fetchrouter.dev
端点
fetchrouter.dev
最近检查

安装

在 SourceWeft 中

  1. 打开 控制台中的 Fetch Router，将其添加到工作区。
  2. 连接 X-API-Key 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/dev.fetchrouter%2Ffetchrouter-mcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "fetch-router": {
      "type": "http",
      "url": "https://fetchrouter.dev/mcp",
      "headers": {
        "X-API-Key": "<YOUR_API_KEY>"
      }
    }
  }
}

README

fetchrouter-mcp

MCP server for Fetch Router: web fetch for AI agents that only bills when the page actually loaded.

Agents often get a 200 OK that is really a Cloudflare challenge, a DataDome block or an empty React shell, and then summarise the error page. Fetch Router checks every page for HTTP errors, block and challenge pages (Cloudflare, DataDome, PerimeterX, Akamai, Imperva, Kasada…), login walls, empty JavaScript shells and text you expect to see. If a check fails it retries through another route, such as a headless browser. Failed fetches cost nothing.

When to use it

  • Your agent reads pages it didn't choose: search results, links from users, sites you don't control.
  • You need to know whether a page really loaded, not just that the request returned 200.
  • Some targets are single-page apps that need a browser, and you don't want to run Playwright yourself.
  • You want to pay per page that works, not per request.

When not to use it

  • Crawling a whole site, mapping links or search. Use a crawler (Firecrawl, Crawl4AI, Apify). Fetch Router does one URL at a time.
  • Pages behind a login or paywall. Not supported, by policy.
  • One or two sites you know well. A plain fetch or your own Playwright script is cheaper.
  • Heavily protected retail and travel sites today. Premium unblocking routes aren't live for customer traffic yet. See the benchmark for what passes.

Setup

Get a free key (500 credits, no card) at https://fetchrouter.dev/#signup.

Remote (no install). Streamable HTTP at https://fetchrouter.dev/mcp, with your key in a header:

sh
claude mcp add --transport http fetchrouter https://fetchrouter.dev/mcp --header "Authorization: Bearer fr_..."

Other clients: URL https://fetchrouter.dev/mcp, header Authorization: Bearer fr_... (or X-API-Key: fr_...).

Claude Code plugin (MCP server plus a verified-fetch skill; asks for your key once and stores it securely):

sh
claude plugin marketplace add JonnoGit/fetchrouter-mcpclaude plugin install fetchrouter@fetchrouter

Local (stdio via npx).

json
{  "mcpServers": {    "fetchrouter": {      "command": "npx",      "args": ["-y", "fetchrouter-mcp"],      "env": { "FETCHROUTER_API_KEY": "fr_..." }    }  }}

Claude Code: claude mcp add fetchrouter -e FETCHROUTER_API_KEY=fr_... -- npx -y fetchrouter-mcp

Tools

  • fetch_page (url, mode?, expect_text?, expect_selector?, max_cost?): returns markdown (default) or HTML, plus which route delivered it and what was tried. max_cost caps credits: 1 = plain HTTP only, 2 (default) allows a browser. If the page can't be loaded, the error says why (blocked:cloudflare, http_404, expect_text_missing…) and nothing is billed.
  • domain_reliability (domain): pass rate per route for a site over the last 30 days, from real verified fetches. Free, no key needed.

How well does it work?

A fixed list of 166 public pages in six site types is fetched every night with plain HTTP and with a headless browser, from a datacenter IP. Results, method and CSV: https://fetchrouter.dev/benchmark

Pricing

1 credit ($0.001) per static page, 2 per browser-rendered page, failures free. Details: https://fetchrouter.dev/#pricing

Environment (stdio)

VariableDefault
FETCHROUTER_API_KEYrequired
FETCHROUTER_BASE_URLhttps://fetchrouter.dev
FETCHROUTER_MAX_CHARS60000 (longer pages are truncated)

Development

sh
npm installnpm run buildFETCHROUTER_API_KEY=fr_... node dist/index.js

The tool definitions live in src/tools.ts and are shared with the hosted endpoint at https://fetchrouter.dev/mcp.

MIT licensed. Operated by One + Done LLC. Contact: [email protected]

来源：README.md，提交 f75ec4d

工具

2

fetch_page

Fetch a web page (verified)

Fetch a public URL and get its content only if it really loaded. Checks for block pages, CAPTCHAs, login walls and empty JavaScript shells, and retries through other routes (including a headless browser) automatically. Billed only on success. 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.

输入参数url必填modemax_costexpect_textexpect_selector

domain_reliability

Which fetch routes work for a site

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.

输入参数domain必填

版本历史

1
  1. v0.1.1最新Nov 3, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分