MCPInstall

volcengine-vefaas

Deploy and manage serverless applications on Volcengine veFaaS through the vefaas CLI. Use when the user has chosen veFaaS or is working with existing veFaaS resources: deploy web apps, static sites, or MCP servers to veFaaS, manage applications and functions (pull/push code, release, rollback, invoke, logs), configure environment variables, manage sandboxes and gateways, inspect veFaaS projects, troubleshoot vefaas CLI/auth/framework/gateway issues, call veFaaS OpenAPI, or look up veFaaS docs and SDK usage. Also trigger on Chinese prompts mentioning 函数服务、veFaaS、vefaas、沙箱实例. If the user wants to deploy to Volcengine without choosing ECS / VKE / veFaaS, prefer volcengine-prepare or volcengine-deploy skill when installed; otherwise this skill handles the veFaaS deployment directly after checking that veFaaS fits.

Installs
109
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/volcengine/volcengine-agent-toolkit --skill volcengine-vefaas
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads volcengine-vefaas automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

volcengine-vefaas

本 skill 指导您使用 @volcengine/vefaas-cli 操作火山引擎 veFaaS,包括应用部署、函数管理、沙箱管理、环境变量、配置、诊断等在火山引擎函数服务控制台能执行的操作以及 OpenAPI 调用。

前置要求

CRITICAL — 执行任何 veFaaS 操作前,MUST 先确认本机 Node.js >= 18、vefaas CLI 版本 >= 0.2.7。

node --version
vefaas --version
vefaas update --check

如果命令不存在,或版本低于 0.2.7,必须先升级;如果 vefaas update --check 发现可更新版本,应提示用户升级后再继续:

npm i -g @volcengine/vefaas-cli@latest
vefaas --version

旧版 CLI 以 @volcengine/vefaas 包名或 volcengine-vefaas-latest.tgz 安装,同样占用 vefaas 命令;此时安装新包会报 EEXIST ... bin/vefaas,版本仍停在旧版本。先 npm uninstall -g @volcengine/vefaas 再安装,并以 vefaas --version 的结果为准。旧版 CLI 执行 vefaas login --sso 可能在授权页提示 请求不合法:identity_type,按上面步骤升级即可。

文档检索能力(免登录)—— vefaas doc 可在终端检索 veFaaS 官方文档,无需登录、只读、不计费。这是本 skill 回答 veFaaS 概念/能力/选型/计费/SDK 用法等问题、以及写 SDK/OpenAPI 代码时的权威知识来源,详见下文「文档优先(doc-first)协议」。运行 vefaas doc --help 确认可用;若不可用,先按上面的方式升级 CLI。

本 skill 随 volcengine-agent-toolkit 分发;升级 CLI 时用 npm i -g 或 vefaas update --skip-skills,不要再安装 CLI 自带的 vefaas skill,避免与本 skill 重复。

适用场景

使用本 skill:

  • 前提:部署目标已选定为 veFaaS,或操作对象是已有的 veFaaS 资源。用户只说「部署到火山引擎」而未选定 ECS / VKE / veFaaS 时,若已安装 volcengine-prepare 或 volcengine-deploy skill,先交给它们分析和选择,选定 veFaaS 后再回到本 skill;未安装时由本 skill 直接处理,先按 应用工作流 的「veFaaS 适配检查」确认项目适合 veFaaS。
  • 用户要把本地项目、网站、API 服务、Node.js 服务、Python 服务或静态站点部署到火山引擎 veFaaS。
  • 用户要基于模板创建 serverless 应用,或把已有项目接入 veFaaS。
  • 用户要查看控制台概览、线上访问地址、发布记录、日志或资源用量。
  • 用户要配置环境变量、调整构建命令、启动命令、端口或资源配置,或删除已有应用。
  • 用户要管理线上函数:创建、查看、发布、回滚、调用、日志、实例、任务、扩缩容策略、触发器、依赖、WebShell。
  • 用户要拉取云端函数代码、本地修改后推送或重新部署。
  • 用户要管理沙箱应用、沙箱实例、沙箱镜像、沙箱日志、沙箱 WebShell。
  • 用户要排查部署失败、鉴权失败、框架检测错误、网关缺失、配置不一致或 OpenAPI 调用失败。
  • 用户明确要调用 veFaaS OpenAPI action,或高阶命令无法覆盖目标操作。
  • 用户第一次接触 veFaaS、不清楚它是什么或如何上手,需要 landing 引导(无需先登录即可开始)。
  • 用户询问 veFaaS 的概念、能力边界、资源选型、计费、限额、触发器等问题,需要基于官方文档准确回答。
  • 用户要把 MCP Server(STDIO / SSE / Streamable-HTTP)部署到 veFaaS。
  • 用户要在自己的代码里接入 veFaaS SDK(Go/Python/Node)或调用 OpenAPI,需要参照官方示例辅助开发。

资源心智模型

  • 函数是 veFaaS(函数服务)的核心资源,承载代码/镜像、版本、实例、日志、资源规格和扩缩容策略;函数实例通常由平台按流量和策略动态扩缩容。
  • 应用是在函数基础上编排应用级逻辑后的产品形态,包含整体版本管理、APIG 触发器关联、Git 仓库自动触发部署等,用于让用户更方便地发布并访问应用。
  • 沙箱是一种特殊/定制的函数,Function、Revision、Instance 模型与函数类似,但必须基于已预热镜像创建,适合代码沙箱、模型评测等秒级拉起隔离环境的场景;沙箱实例需要主动创建,并支持暂停、恢复、关闭和调整过期时间。
  • 需要更细的资源关系、ID 使用规则或 CLI target 映射时,读取 CLI 与版本。

CRITICAL 工作流分流

CRITICAL — 先判断用户意图是「知识类」还是「执行类」,再分流:

  • 知识类(问概念/能力/选型/计费/限额;第一次用、要 landing 上手引导;要写 SDK/OpenAPI 集成代码)→ 走「文档优先(doc-first)工作流」:先用 vefaas doc 检索官方文档,基于文档回答或写代码,通常无需登录。继续前 MUST 读取 文档检索与 doc-first。
  • 执行类(部署、发布、回滚、调用、管理函数/应用/沙箱/网关等真实资源操作)→ 走下面对应的执行工作流。
  • 混合类(如“帮我部署这个项目,顺便讲下计费”)→ 先用 doc-first 答疑,再走执行工作流。

下面是执行类工作流的分流规则:

CRITICAL — 已确定使用 veFaaS 后,用户说“部署项目 / 网站上线 / API 上线 / serverless 应用 / 查看访问地址”时,默认走应用工作流,不要直接创建函数。

应用工作流使用 vefaas init、vefaas inspect、vefaas link、vefaas deploy、vefaas domains、vefaas env、vefaas config、vefaas app、vefaas overview、vefaas resource。继续前 MUST 读取 应用工作流。

CRITICAL — 只有用户给出已有函数 ID/name,或明确说“函数 / function / fn / 拉取函数代码 / 发布函数 / 回滚函数 / 函数日志”时,才走函数工作流。

函数工作流使用 vefaas fn ...、vefaas pull、vefaas push、vefaas deploy --funcId。继续前 MUST 读取 函数管理。

CRITICAL — 用户说“沙箱 / sandbox / 沙箱实例 / 临时实例 / 实例暂停恢复 kill / 沙箱镜像”时,走沙箱工作流。

沙箱工作流必须区分 sandbox application 与 sandbox instance;application ID 和 instance name 不能混用。继续前 MUST 读取 沙箱管理。

CRITICAL — 高阶命令能完成任务时,不要直接使用 vefaas api。

只有在高阶命令缺失、用户明确要求 OpenAPI、或需要底层 action 字段时,才使用 OpenAPI 工作流。继续前 MUST 读取 OpenAPI 调用,并先执行 vefaas api <Action> --help 查看参数结构。

必读 Reference 协议

执行对应任务前,MUST 读取对应 reference;不要只凭本文件的速查命令执行复杂操作。

场景必读文件
答疑、landing 引导、查官方文档、写 SDK/OpenAPI 集成代码文档检索与 doc-first
安装、升级、确认 CLI 版本CLI 与版本
登录、检查凭据、恢复鉴权认证与凭据
初始化模板、部署应用、link、inspect、domains、应用 env/config应用工作流
管理函数、代码、发布、回滚、日志、调用、配置、扩缩容函数管理
函数 APIG 触发器、沙箱网关路由配置、APIG route 绑定与编辑触发器与 APIG Route
管理 sandbox application / instance沙箱管理
直接调用 veFaaS OpenAPIOpenAPI 调用
部署 MCP Server、run.sh、mcp-proxy、协议判断MCP 部署
排查失败、诊断环境故障排查

全局执行规则

  • 非交互式 AI/CI 场景中,目标明确时优先加 --yes。
  • 需要解析输出时,优先使用 --output json,再配合 --jq、--fields、--limit。
  • 不确定命令或 flag 时,先运行 vefaas <command> --help,不要猜参数。
  • 遇到凭据、项目配置、本地环境或 OpenAPI 连通性问题时,优先执行 vefaas doctor。
  • --debug 仅用于诊断;debug 输出和 ~/.vefaas/logs/ 可能包含敏感请求/响应信息。
  • 不要把 Access Key ID、Secret Access Key、session token、OAuth/OIDC token、数据库连接串、.env value 明文回显给用户。
  • vefaas doc 系列只读、免登录、不计费,可自由多次调用,不受下文「高风险操作协议」约束。agent 自用文档时一律加 -o json,读 data.markdown(正文)或 data.results[](搜索结果);仅当要把文档渲染给人看时才用默认 text 模式。

文档优先(doc-first)协议

涉及 veFaaS 的概念、能力、选型、计费、限额、SDK 用法、OpenAPI 参数时,MUST 先用 vefaas doc 检索官方文档,再作答或写代码;禁止凭记忆直接回答这些具体事实。

  1. 高频主题用内置别名直达:intro(产品介绍)、quickstart(快速入门)、cli、sdk(SDK 概览)、api。SDK 各语言用子命令 vefaas doc sdk go|python|node -o json。
  2. 长尾问题(计费、限额、触发器、网关、某具体功能)先 vefaas doc search <关键词> -o json,从 data.results[] 按 title + path(面包屑)挑最匹配的叶子文档,取其 documentId,再 vefaas doc --id <id> -o json 读 data.markdown。
  3. 答疑:答案不得超出 data.markdown;计费/限额/配额必须引用文档原文数值;回答末尾附出处 data.url 与更新时间 data.updatedTime。
  4. 写 SDK/OpenAPI 代码:先取官方示例(vefaas doc sdk go|python|node -o json)作骨架;用 vefaas doc sdk methods <Action> -o json 查该 Action 的请求字段(type + 说明 + 嵌套),可加 --lang 拿请求示例。禁止凭记忆生成 SDK 调用。
  5. vefaas doc --id 命中目录节点会报 not-found(目录节点无正文)→ 回到 search 结果换一条更深的叶子文档。
  6. search 无结果时用 vefaas doc tree -o json 浏览目录;仍找不到则如实说明官方文档未覆盖,不要编造。

完整的三类场景工作流(landing / 答疑 / SDK 接入)见 文档检索与 doc-first。

高风险操作协议

以下操作会影响线上行为或销毁资源,执行前必须确认目标资源和用户意图:

  • 删除应用、删除函数、删除沙箱应用、删除沙箱镜像。
  • kill / pause / resume sandbox instance。
  • 函数或沙箱 rollback。
  • 修改生产环境触发器等。

处理规则:

  1. 先展示将要操作的资源标识(app/function/sandbox ID 或名称)和动作。
  2. 如果目标不唯一或来源只是用户口述名称,先 list/info 消歧。
  3. 用户明确确认后再执行;不要静默添加 --yes 绕过确认。
  4. 用户拒绝或目标不清楚时停止,不要自行猜测替代目标。

应用删除特殊规则: 删除 veFaaS Application 前先执行 vefaas app delete --id <app-id> --check -o json 做前置检查。若检查发现 APIG/NAT/EIP 等共享或可能持续计费资源,非交互场景必须显式传 --ack-shared-resources;不要用全局 --yes 代替这类风险确认。只有用户明确接受跳过前置阻塞时,才使用 --force --yes,并说明关联资源可能不会被自动清理。

目标消歧规则

  • App name、function name、sandbox name 可能不唯一;涉及写操作时,优先使用 ID。
  • 只有名称没有 ID 时,先用 list / info / config list / config pull 获取真实资源信息。
  • 新应用部署需要 gateway name;先执行 vefaas gateway list --first。如果没有返回,停止并询问用户提供已有网关或先创建网关。
  • 当前目录存在 .vefaas/config.json 时,不代表一定是用户想操作的目标;涉及线上写操作前先 vefaas config list 确认。
  • sandbox application ID 与 sandbox instance name 不可互换;实例操作前先 vefaas sandbox instance list --id <sandbox-application-id>。

FAQ

What does the volcengine-vefaas skill do?

Deploy and manage serverless applications on Volcengine veFaaS through the vefaas CLI. Use when the user has chosen veFaaS or is working with existing veFaaS resources: deploy web apps, static sites, or MCP servers to veFaaS, manage applications and functions (pull/push code, release, rollback, invoke, logs), configure environment variables, manage sandboxes and gateways, inspect veFaaS projects, troubleshoot vefaas CLI/auth/framework/gateway issues, call veFaaS OpenAPI, or look up veFaaS docs and SDK usage. Also trigger on Chinese prompts mentioning 函数服务、veFaaS、vefaas、沙箱实例. If the user wants to deploy to Volcengine without choosing ECS / VKE / veFaaS, prefer volcengine-prepare or volcengine-deploy skill when installed; otherwise this skill handles the veFaaS deployment directly after checking that veFaaS fits.

How do I install volcengine-vefaas?

Run npx skills add https://github.com/volcengine/volcengine-agent-toolkit --skill volcengine-vefaas in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/volcengine-vefaas/ (personal) or .claude/skills/volcengine-vefaas/ (project).

Which AI agents can use volcengine-vefaas?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is volcengine-vefaas safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains volcengine-vefaas?

It is published by volcengine in volcengine/volcengine-agent-toolkit. It has 109 recorded installs.

More from volcengine/volcengine-agent-toolkit

View all →

volcengine-tosutil

volcengine/volcengine-agent-toolkit

Use when the user mentions tosutil, TOS object storage, bucket/object operations, batch upload or download, object metadata, TOS connectivity, or errors such as 403/network/argument failures. 围绕火山引擎对象存储 tosutil 生成与校验命令、规划桶/对象操作并诊断错误;当用户提到 tosutil、TOS 桶对象管理、批量上传下载或相关排障时调用。

211 installs

volcengine-cli

volcengine/volcengine-agent-toolkit

Create and manage Volcengine cloud resources using the Volcengine CLI (ve command). Supports all Volcengine services including ECS, VPC, CLB, RDS, Redis, and more. Trigger this skill whenever the user asks to create, query, modify, or delete cloud resources on Volcengine, mentions the ve command, says "volcengine CLI", or describes infrastructure tasks such as "create an ECS instance", "set up a VPC", "list security groups", "allocate an EIP". Also trigger on Chinese prompts mentioning "火山引擎" or "火山" (e.g., "火山引擎上有哪些 ECS"、"查一下我火山的云服务器"、 "火山引擎创建一个 VPC"、"火山的 Redis 实例列一下"). Also trigger when the user encounters errors from ve commands and needs troubleshooting help. Also use for TOS bucket/object operations, tosutil (sometimes written tosutils), Ark CLI / arkcli model discovery, inference, generation, endpoints, fine-tuning, plans, or usage, and TLS (日志服务) / volclog log search, analysis, ingest, export, or LogCollector collection, through ve tosutil, ve arkcli and ve volclog.

Data & Databases208 installs

volcengine-knowledge-search

volcengine/volcengine-agent-toolkit

使用 ve docs search/fetch 检索火山引擎官方文档并获取全文。Use when 用户咨询火山引擎产品的概念、用法、计费规则、部署步骤、最佳实践或服务条款,或提供 www.volcengine.com/docs/、docs.volcengine.com/docs/ 链接需要阅读正文时。

Docs & Writing167 installs

volcengine-api

volcengine/volcengine-agent-toolkit

Query and answer questions about Volcengine API specifications. Use when the user asks about API parameters, error codes, request methods, enum values, required fields, response structures, pagination, parameter dependencies, service capability lists, API availability, or API comparisons, even if they do not explicitly say "API". Typical intent includes checking what an action supports, which fields are required, what values a parameter accepts, why an API returns a specific error, how to pass nested or body parameters, how pagination works, what an API response contains, whether a batch operation exists, what services or versions expose an operation, or how two APIs differ. Use API Explorer data as the authoritative source and preserve constraints, examples, and caveats found in the spec. Answer in Chinese or English. When the user needs runnable SDK code, language-specific examples, or SDK configuration, hand off to volcengine-sdk-generator. When they need CLI operations, hand off to

Backend & APIs127 installs

volcengine-troubleshooting

volcengine/volcengine-agent-toolkit

Open the skill to read its SKILL.md instructions.

126 installs

volcengine-find-skills

volcengine/volcengine-agent-toolkit

List, select, and install Volcengine skills from the volcengine-skills marketplace. Use when a user asks which Volcengine skill or plugin handles a task, wants to browse every available skill, needs an optional skill that is not currently installed, or asks to install or check the installation status of a Volcengine skill. Also use to discover any core skill, including this finder. Use as a fallback during a Volcengine operation when the currently loaded or installed skills cannot cover the required product, tool, or workflow; inspect the full catalog, select the missing capability, and install it.

Popular devops & cloud skills

View category →

microsoft-foundry

microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure

OfficialDevOps & Cloud579.1K installs

azure-diagnostics

microsoft/azure-skills

Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target port mismatch, troubleshoot functions, function telemetry missing or stopped after a config/connection-string change, troubleshoot AKS, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM password, NSG or firewall blocking, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource health, root cause of errors, troubleshoot event hubs, troubleshoot service bus, messaging SDK error, AMQP connection failure, message lock lost, lock renewal during long-running processing, service bus dead letter.

OfficialDevOps & Cloud569.8K installs

azure-prepare

microsoft/azure-skills

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up azd infrastructure, modernize app for Azure with azd, deploy with azd, function app, timer trigger, service bus trigger, event-driven function, managed identity, generate Bicep, generate Terraform, create and deploy to Azure.

OfficialDevOps & Cloud569K installs

azure-ai

microsoft/azure-skills

Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.

OfficialDevOps & Cloud568.8K installs

azure-deploy

microsoft/azure-skills

Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.

OfficialDevOps & Cloud568.6K installs

azure-validate

microsoft/azure-skills

Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prerequisites before deploying. WHEN: validate my app, check deployment readiness, run preflight checks, verify configuration, check if ready to deploy, validate azure.yaml, validate Bicep, test before deploying, troubleshoot deployment errors, validate Azure Functions, validate function app, validate serverless deployment, verify RBAC roles, check role assignments, review managed identity permissions, what-if analysis, validate Container Apps deployment.

OfficialDevOps & Cloud568K installs