Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
bytedance avatar

Byted Volcengine Flink

  • 31 installs
  • 411 repo stars
  • Updated August 4, 2026
  • bytedance/agentkit-samples

byted-volcengine-flink is a Claude skill that manages Volcengine Flink workloads by routing to four sub-skills and executing tools through flink-mcp.

About

This skill is an aggregator entrypoint for managing Volcengine Flink (based on Apache Flink) workloads. It routes requests to four sub-skills for developing and deploying streaming and batch SQL jobs, read-only diagnosis, resource and fault analysis, and SRE actions like stop, start, restart, scale, and config changes. It executes tools through flink-mcp and requires user confirmation before any change operation.

  • Aggregator entrypoint for Volcengine Flink (Apache Flink) workloads
  • Routes to four sub-skills: dev, diagnosis, resource, SRE
  • Executes tools through flink-mcp

Byted Volcengine Flink by the numbers

  • 31 all-time installs (skills.sh)
  • Ranked #784 of 1,039 Cloud & Infrastructure skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

byted-volcengine-flink capabilities & compatibility

Requires Volcengine access keys and a Flink project; depends on flink-mcp and mcporter.

Capabilities
byted volcengine cloudmonitor
Works with
kafka
Use cases
devops · orchestration
Runs
Runs locally
Pricing
Bring your own API key
From the docs

What byted-volcengine-flink says it does

Entrypoint for managing Volcengine Flink (based on Apache Flink) workloads.
SKILL.md
It intelligently routes requests to four specialized sub-skills and leverages flink-mcp for tool execution.
SKILL.md
npx skills add https://github.com/bytedance/agentkit-samples --skill byted-volcengine-flink

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs31
repo stars411
Last updatedAugust 4, 2026
Repositorybytedance/agentkit-samples

What it does

Develop, deploy, diagnose, and run SRE actions on Volcengine Flink streaming and batch jobs via flink-mcp.

Who is it for?

Streaming/batch Flink job development, diagnosis, and SRE on Volcengine.

When should I use this skill?

Use for developing, deploying, diagnosing, or performing SRE actions on Volcengine Flink jobs.

By the numbers

  • 4 specialized sub-skills
  • 4 required env vars for flink-mcp

Files

SKILL.mdMarkdownGitHub ↗

Byted Volcengine Flink

火山引擎 Flink 聚合技能入口,用于统一处理 Flink 相关需求,并按意图转发到对应子技能文档。

前置环境

在安装并使用本技能前,需要先完成 flink-mcp 前置准备。

1) 安装并验证 mcporter

flink-dev.mdflink-resource.mdflink-sre.md 中的运维/诊断指令依赖 mcporter

可按你的 Python 环境选择任一方式安装:

npm install -g mcporter

安装后验证:

mcporter --help

2) 配置必需环境变量

flink-mcp 启动依赖以下环境变量(缺一不可):

  • VOLCENGINE_ACCESS_KEY
  • VOLCENGINE_SECRET_KEY
  • VOLCENGINE_REGION
  • VOLCENGINE_PROJECT_NAME

示例:

export VOLCENGINE_ACCESS_KEY="your-access-key"
export VOLCENGINE_SECRET_KEY="your-secret-key"
export VOLCENGINE_REGION="cn-beijing"
export VOLCENGINE_PROJECT_NAME="your-flink-project"

3) 在本地 MCP 配置文件中注册 flink-mcp(推荐)

flink-mcp 加入本地 MCP Client 使用的配置文件(通常为 mcp.json 或等效配置文件)。

说明:MCP Client 会根据这段配置拉起 flink-mcp,因此这是默认主路径。

先确保本地已安装 uv / uvx,然后写入如下配置:

{
  "mcpServers": {
    "mcp-server-flink": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/volcengine/mcp-server#subdirectory=server/mcp_server_flink",
        "mcp-server-flink",
        "-t",
        "streamable-http"
      ],
      "env": {
        "VOLCENGINE_ACCESS_KEY": "${VOLCENGINE_ACCESS_KEY}",
        "VOLCENGINE_SECRET_KEY": "${VOLCENGINE_SECRET_KEY}",
        "VOLCENGINE_REGION": "${VOLCENGINE_REGION}",
        "VOLCENGINE_PROJECT_NAME": "${VOLCENGINE_PROJECT_NAME}",
        "UV_INDEX_URL": "https://mirrors.ivolces.com/pypi/simple/"
      }
    }
  }
}

4) 可选:手动启动 flink-mcp(仅用于联调/排障)

当需要独立验证服务是否可启动时,可在终端手动执行:

uvx --from git+https://github.com/volcengine/mcp-server#subdirectory=server/mcp_server_flink mcp-server-flink -t streamable-http

子技能引用与路由

根据用户需求,将任务路由到以下子技能:

  • 开发/部署 Flink SQL:flink-dev.md
  • 只读诊断(禁止变更操作):flink-diagnosis.md
  • 资源与故障分析:flink-resource.md
  • SRE 运维变更(启停/重启/扩缩容/参数修改):flink-sre.md

路由规则

1. 用户表达“创建 SQL / 开发 SQL / 部署 SQL / 调试 SQL”时,优先使用 flink-dev.md。 2. 用户明确要求“只读排查、不做任何变更”时,必须使用 flink-diagnosis.md。 3. 用户询问故障根因、OOM、Checkpoint、性能问题、连接问题时,优先使用 flink-resource.md。 4. 用户要求执行运维动作(启动、停止、重启、扩容、缩容、改配置)时,必须使用 flink-sre.md,且先做风险确认。

执行原则

  • 在信息不足时,先补齐关键参数:项目名、任务名、时间范围、目标动作。
  • 任何变更类操作(尤其在 flink-sre.md 中)都必须先让用户确认风险。
  • 当用户只需要排查时,坚持只读工具链,不触发启动/停止/部署等动作。

Related skills

FAQ

How does it execute Flink actions?

It leverages flink-mcp for tool execution and routes intents to four specialized sub-skills (dev, diagnosis, resource, SRE).

What is required before change operations?

Any change operation, especially in flink-sre, must first have the user confirm the risk.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.