io.github.GSterlingPress由 GitHub 帳號 GSterlingPress 發布v0.7.6更新於 Oct 25, 2026
Choose HTTP, browser, machine endpoint, or avoid before an agent visits an unfamiliar URL.
發布方自己的服務：Preflight
遠端 MCP 服務，讓助理在造訪陌生網址前先取得建議路線（HTTP、瀏覽器、機器端點或避免）。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.GSterlingPress%2Fpreflight/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"preflight-url-routing-for-ai-agents": {
"type": "http",
"url": "https://preflight-api-production-01a2.up.railway.app/mcp"
}
}
}Before your AI agent visits a URL, ask us how to get there.
PREFLIGHT is routing intelligence for browser, research and shopping agents. Given a URL, it recommends the cheapest likely route to try first: HTTP, BROWSER, MACHINE_ENDPOINT, or AVOID.
The long-term product is a machine map of the web: not what is on the web, but how should a machine interact with this destination?
Base URL:
https://preflight-api-production-01a2.up.railway.app
REST — use the actual URL your agent is about to visit:
For example, if your agent is about to inspect a product, documentation page, article, booking page, or SaaS site, pass that real destination to PREFLIGHT first. example.com is only a documentation placeholder and should not be used when a real task URL exists.
Remote MCP:
https://preflight-api-production-01a2.up.railway.app/mcp
The MCP server exposes two tools:
preflight_check — call this before fetching or browser-rendering an unfamiliar real URL.preflight_feedback — report whether the chosen route worked so PREFLIGHT can improve future recommendations.Example tool intent:
Before opening the URL from my current task, use PREFLIGHT to decide whether ordinary HTTP, a browser, a machine-readable endpoint, or avoidance is the best first route.
Fetching first can be wasteful. A destination may be directly readable over HTTP, require browser rendering, expose a smaller machine endpoint, block automation, require authentication/payment, or carry access signals that make a fetch undesirable. PREFLIGHT tries to answer that routing question before the expensive step.
Responses combine direct probe signals, cached domain knowledge, and sufficiently strong observed route feedback. They can include status, redirects, robots/access hints, estimated token size, JavaScript-shell hints, structured-data signals, machine endpoints, latency, confidence, cache age, and learned route evidence.
PREFLIGHT stores aggregated success/failure evidence rather than page content or user identities. URL-level learning requires at least 5 samples at 80% success; domain-level learning requires at least 10 samples at 85% success. Feedback never overrides a current AVOID decision from live safety/access/robots signals.
AGENTS.md tells coding/AI agents exactly when to use PREFLIGHT.llms.txt gives LLMs a compact machine-readable explanation, live endpoints, and usage rule.openapi.json exposes REST operations in OpenAPI 3.1 format for tool importers and generated clients.mcp.json contains a generic remote MCP client configuration.docs/AGENT-INTEGRATIONS.md contains copy/paste integration patterns for browser, research, shopping, coding, MCP, and REST agents.server.json contains official MCP Registry metadata for the public Streamable HTTP server./mcp supports MCP initialize, initialized notification, ping, tools/list, and tools/call.Search/discovery concepts: AI agent URL routing, browser-agent preflight, choose HTTP vs browser, machine-readable endpoint discovery, reduce agent browsing tokens, agent web routing, pre-fetch routing intelligence, AI browser cost reduction, route before crawl, agent URL access intelligence.
GET /ready verifies the data directory is writable. Railway deployments use /data; mount a persistent volume there when long-term feedback persistence is required. PREFLIGHT_FEEDBACK_KEY optionally bearer-protects feedback writes while keeping route checks public. npm run smoke:live exercises the public route/feedback cycle.
benchmarks/sites.json contains a cross-category live corpus. Run npm run benchmark. The scheduled benchmark records route, status, latency, token estimate and machine endpoints and preserves machine-readable reports for trend analysis.
PREFLIGHT blocks localhost, private/link-local network addresses, credential-bearing URLs, non-HTTP protocols, and unsafe redirect destinations. Endpoint discovery and negotiated probes go through the same SSRF-safe fetch layer. MCP validates browser Origins, and route feedback cannot relax an active AVOID result.
Requires Node.js 20+.
PREFLIGHT is not a crawler, browser farm, search engine or site-owner audit tool. Its job is narrower:
Real URL in → cheapest reliable machine route out.
來源：README.md，提交 c5ce1cd
Check URL Before Fetching
Before fetching, crawling, scraping, opening, or browser-rendering an unfamiliar http/https URL, call this with the ACTUAL destination URL. Returns the best first route: HTTP, BROWSER, MACHINE_ENDPOINT, or AVOID, plus access/JS/size/cost hints. Do not substitute example.com when a real task URL is available.
url必填Report PREFLIGHT Outcome
After following a PREFLIGHT recommendation, report whether the chosen route worked so PREFLIGHT can improve future recommendations.
url必填route必填outcome必填latencyMs已滿足適用檢查項的 90%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
請在儲存庫或註冊中心條目中宣告授權條款。
social.preflight官方發布者
託管式社群媒體排程伺服器，讓助理起草、依規則檢查、排程並發佈貼文到 12 個平台。
由 GitHub 帳號 showflexinc 發布
遠端預檢服務，在執行重建前檢查 SQLite 資料表重建複製對應的結構。
由 GitHub 帳號 Wolfe-Jam 發布
在發布前檢查 MCP Registry 項目：README 中的 mcp-name 行、server.json 的發布規則，以及伺服器名稱。
由 GitHub 帳號 showflexinc 發布
CSV row-structure inspection (inspect_parts) and manifest comparison (compare_manifest).
由 GitHub 帳號 showflexinc 發布
針對JSONL工具對話訓練資料的結構化預檢。AI 翻譯
GET /v1/check?url=<encoded-actual-destination-url>POST /v1/feedbackContent-Type: application/jsonAuthorization: Bearer <feedback-key> # when protection is enabled{ "url": "https://merchant.example/product/123", "route": "BROWSER", "outcome": "success", "latencyMs": 840}npm testnpm start