Vibe + Cloudflare
Mistral AIMistral AI 推出的编程 Agent,适用于终端、IDE 和云端工作流,可读取文件、运行命令、编写代码和创建拉取请求。
-
安装 Vibe
在 macOS 或 Linux 上安装 Vibe 命令行界面 (CLI)。其他安装方法请参阅 Vibe 安装指南 ↗。
curl -LsSf https://mistral.ai/vibe/install.sh | bash -
设置 Vibe
完成设置流程。使用你的 Mistral 账户登录,或输入 API 密钥。
vibe --setup -
安装 Cloudflare Skills
在项目根目录为当前项目安装 Cloudflare Skills。Vibe 会从
.agents/skills/发现项目 Skills。npx skills add cloudflare/skills --skill '*' --yesyarn dlx skills add cloudflare/skills --skill '*' --yespnpx skills add cloudflare/skills --skill '*' --yes -
添加 Cloudflare MCP 服务器
将 Cloudflare Model Context Protocol (MCP) 服务器添加到
~/.vibe/config.toml。请备份现有文件并保留无关设置。更新已存在的条目,而不是添加重复项。[[mcp_servers]] name = "cloudflare" transport = "streamable-http" url = "https://mcp.cloudflare.com/mcp" [mcp_servers.auth] type = "oauth" scopes = []有关来源和配置详情,请参阅 cloudflare/mcp ↗ 和 cloudflare/mcp-server-cloudflare ↗。
-
启动并授权 Vibe
从项目根目录启动 Vibe。对于现有项目,使用包含
wrangler.jsonc的目录。vibe如果 Vibe 已在运行,改为输入
/reload。然后输入/mcp status检查服务器。授权 Cloudflare MCP 服务器:/mcp login cloudflare在浏览器中完成 OAuth 流程。
-
尝试提示词
例如:
使用 Workers for Platforms,让客户在隔离环境中部署自己的代码。
展开任意部分以了解更多。
Cloudflare Skills
持久的平台上下文,教会 Agent Cloudflare 如何工作。
Skills 是 Agent 按需加载的说明。 cloudflare/skills 包覆盖平台的每一层 — 因此 Agent 了解你的约定,无需你反复解释。
- agents-sdkBuild, debug, or review Cloudflare Agents SDK applications using the agents package.
- basinBuild and troubleshoot Cloudflare Basin analytics workflows with Basin Pipelines, Basin Catalog, and Basin SQL. Use for streaming data into R2 Iceberg tables, managing catalogs, or querying those tables; also use for requests using the former Data Platform, Pipelines, R2 Data Catalog, or R2 SQL names.
- cf-cliCloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in a project.
- cloudflareDiscover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security. Use for architecture and product selection, including when the user describes a need without naming a Cloudflare product; then find the relevant skill or documentation. Also use when a Cloudflare-proxied site shows a Cloudflare error page, a `52x` status, a 1xxx error code, or a Cloudflare `403`, to decide whether to fix Cloudflare configuration or the origin.
- cloudflare-app-bootstrapGet a Cloudflare Workers app to a working local request by connecting its bindings, secrets, and initial data, then verifying real application behavior. Use for app setup or onboarding after the project exists; use frameworks-on-cloudflare or cf-cli to create or configure the project, and wrangler or cf-cli for isolated commands.
- cloudflare-email-serviceImplement or troubleshoot Cloudflare Email Sending and Email Routing integrations and their delivery configuration.
- cloudflare-oneDesign, configure, troubleshoot, or review Cloudflare One Zero Trust and SASE deployments. Use cloudflare-one-migrations for migration planning from other vendors. Also use when an agent, script, crawler, or other non-browser client needs to reach a webpage or API protected by Cloudflare Access.
- cloudflare-one-migrationsAssess and plan migrations from existing VPN, SWG, or SASE platforms to Cloudflare One, including policy mapping, parity gaps, and rollout.
- durable-objectsBuild, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
- frameworks-on-cloudflareBuild, migrate, and deploy web-framework applications on Cloudflare Workers. Use when a framework project such as Astro, SvelteKit, React Router, TanStack Start, Nuxt, Hono, or a React or Vue SPA targets Cloudflare, or when a framework repository contains Workers deployment configuration.
- gateway-workersBuild, debug, or review Cloudflare Workers invoked by the Forward action in Gateway HTTP policies, including the GatewayMiddleware entrypoint, Gateway types, context, and continuation.
- k2Build and troubleshoot Cloudflare K2 or K2 Streams durable logs. Use for stream setup, producing from Workers or HTTP, configuring retention and inputs, and consuming through subscriptions.
- nextjs-on-cloudflareBuild, migrate, and deploy Next.js apps on Cloudflare Workers with vinext. Use when starting a Next.js project on Cloudflare, moving an existing app to Workers, choosing between vinext and OpenNext, or setting up vinext for Workers. For setup, migration, or deployment, install vinext's upstream skills with `npx skills add cloudflare/vinext` if missing, then read and follow the applicable skill and docs.
- sandbox-migrate-to-nextMigrate Cloudflare Sandbox apps from stable @cloudflare/sandbox to @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-next for apps already on the preview.
- sandbox-nextBuild or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.
- sandbox-stableBuild or maintain Cloudflare Sandbox apps on the stable @cloudflare/sandbox package. Use sandbox-next for preview apps and sandbox-migrate-to-next for stable-to-preview migrations.
- turnstile-spinSet up, repair, or migrate to Cloudflare Turnstile bot verification in an existing frontend and backend, including server-side Siteverify.
- web-perfAudit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.
- workers-best-practicesCloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
- workers-developmentRun, inspect, and debug Cloudflare Workers during local development with cf dev, wrangler dev, or the Cloudflare Vite plugin, using Local Explorer to read and seed binding data and query local traces and logs. Also routes production debugging to Workers observability. Use for debugging requests whether or not the project uses Wrangler.
- workers-profilingProfile or debug CPU usage and memory allocation in deployed Cloudflare Workers and Durable Objects. Then use this information to optimize your code.
- wranglerRun or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, Previews, deployment, and resource management. For new projects and projects without a Wrangler configuration file, use the cf CLI instead.
MCP 服务器
实时访问 Cloudflare API、文档和可观测性。
MCP 服务器提供类型化工具,以便在运行时调用 Cloudflare。有两种选择:Code Mode — 一台覆盖整个 Cloudflare API 的服务器(约 1,000 个 token 覆盖 2,500+ 个端点)— 或者一组聚焦特定领域的服务器,托管在 cloudflare/mcp-server-cloudflare 仓库中。完整目录也在 Cloudflare 的 MCP 服务器 文档中。
- Cloudflare API MCP ServerCode ModeBest when you want broad access across Cloudflare's APIs through code executionhttps://mcp.cloudflare.com/mcp
- Code mode APICode ModeBroad access to the full Cloudflare API via code execution, with minimal token overheadhttps://mcp.cloudflare.com/mcp
- Browser Run serverFetch web pages, convert them to markdown and take screenshotshttps://browser.mcp.cloudflare.com/mcp
- Cloudflare Blog serverSearch and read posts from the Cloudflare Bloghttps://blog.mcp.cloudflare.com/mcp
- Cloudflare One CASB serverQuickly identify any security misconfigurations for SaaS applications to safeguard users & datahttps://casb.mcp.cloudflare.com/mcp
- Container serverSpin up a sandbox development environmenthttps://containers.mcp.cloudflare.com/mcp
- Demo Day serverDemonstrate a minimal Cloudflare MCP serverhttps://demo-day.mcp.cloudflare.com/mcp
- Digital Experience Monitoring serverGet quick insight on critical applications for your organizationhttps://dex.mcp.cloudflare.com/mcp
- Documentation serverGet up-to-date reference information on Cloudflarehttps://docs.mcp.cloudflare.com/mcp
Wrangler CLI
本地开发、部署和 Workers 专用命令。
使用 Wrangler 进行本地开发、部署以及运行产品专用命令,例如 wrangler d1 migrations apply 或 wrangler tail。 捆绑的 wrangler Skill 会教 Agent 何时使用它。
面向 Agent 的文档
为 Agent 优化的、节省 token 的参考资料。
在任意 Cloudflare 文档 URL 后追加 /index.md 即可获得干净的 Markdown 版本。每个顶级产品部分也有自己的 llms.txt — 一份适合单个上下文窗口的页面索引。常用文件包括:
- developers.cloudflare.com/llms.txt — 包含每个 Cloudflare 产品的目录。
- developers.cloudflare.com/workers/llms.txt
- developers.cloudflare.com/agents/llms.txt
- developers.cloudflare.com/r2/llms.txt
- developers.cloudflare.com/d1/llms.txt
关于这些文档如何面向 Agent 组织的完整概览,请参阅面向 Agent 的文档指南。
- Cloudflare API MCP 服务器使用 Code Mode — Vibe 针对类型化的 API 编写 JavaScript,在约 1,000 个 token 内访问 2,500+ 个端点中的任何一个。
- 将项目说明存储在
AGENTS.md中。Vibe 会从项目根目录和相关子目录加载说明。 - 使用
vibe --agent plan启动 Vibe,以便在不修改项目的情况下进行检查。
我是应该使用 Skills、MCP 服务器、Wrangler CLI,还是全部三者?
三者都要用。Skills 提供 Cloudflare 实现指导。MCP 服务器 提供最新文档和经过身份验证的 API 工具。Wrangler 处理 本地开发、部署和 Workers 特定命令。
如何向 Vibe 授予我 Cloudflare 账户的访问权限?
运行 /mcp login cloudflare,然后在浏览器中完成授权流程。
我可以在 Vibe 中使用其他模型提供商吗?
可以。Vibe 支持 Mistral 托管的模型、兼容的 API 提供商以及本地
模型。在 ~/.vibe/config.toml 中配置模型和提供商。
Vibe 是开源的吗?
是的。Vibe CLI 以 Apache 2.0 许可在 mistralai/mistral-vibe ↗ 仓库中提供。
MCP 服务器未连接
确认 ~/.vibe/config.toml 中的条目与快速入门一致。输入
/reload,然后输入 /mcp status。如果服务器报告 needs_auth,输入
/mcp login <name>。
MCP 服务器身份验证失败
输入 /mcp logout cloudflare,然后输入 /mcp login cloudflare。在浏览器中完成
新的授权流程。
Cloudflare Skills 不可用
输入 /reload 以重新加载 Vibe 配置和 Skills。如果 Skills 仍
未加载,确认安装程序已将它们写入项目的
.agents/skills/ 目录。
获取到关于 Cloudflare 产品的过时信息
将 Vibe 指向 developers.cloudflare.com/llms.txt 以获取所有产品的目录。
使用 developers.cloudflare.com/<product>/llms.txt 获取特定产品的索引。
Cloudflare 不只是 Agent 的部署目标,也是用来构建你自己 Agent 的完整技术栈。