volcano-agent-sdk MCP — ユースケース, インストール & ライブデモ

なぜ使うのか

主な機能

100+ LLM models across major providers
Automatic tool selection from multiple MCP endpoints
Multi-agent crews with task delegation
Parallel / branching / loop execution patterns
OpenTelemetry traces, native OAuth for MCPs, connection pooling

ライブデモ

実際の動作

volcano-agent-sdk.replay ▶ 準備完了

0/0

インストール

クライアントを選択

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "volcano-agent-sdk": {
      "command": "npx",
      "args": [
        "-y",
        "volcano-agent-sdk"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "volcano-agent-sdk": {
      "command": "npx",
      "args": [
        "-y",
        "volcano-agent-sdk"
      ],
      "_inferred": true
    }
  }
}

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "volcano-agent-sdk": {
      "command": "npx",
      "args": [
        "-y",
        "volcano-agent-sdk"
      ],
      "_inferred": true
    }
  }
}

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "volcano-agent-sdk": {
      "command": "npx",
      "args": [
        "-y",
        "volcano-agent-sdk"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "volcano-agent-sdk",
      "command": "npx",
      "args": [
        "-y",
        "volcano-agent-sdk"
      ]
    }
  ]
}

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.config/zed/settings.json

{
  "context_servers": {
    "volcano-agent-sdk": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "volcano-agent-sdk"
        ]
      }
    }
  }
}

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add volcano-agent-sdk -- npx -y volcano-agent-sdk

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方： volcano-agent-sdk

Build a coding agent that uses GitHub + Sentry MCPs

👤 TS devs building internal automation ⏱ ~60 min advanced

使うタイミング： You want a programmable agent, not a chat session.

前提条件

Node 20+ — Standard
MCP endpoints for the tools you want (github, sentry, etc.) — Either existing public or your own deploys

フロー

Install + scaffold

npm install @volcano.dev/agent and write a minimal agent that connects to github + sentry MCPs with Anthropic as the model.✓ コピーしました

→ Running TS project
Write the task

The agent's task: every 15 min, find new Sentry errors, correlate to GitHub commits via MCP, draft revert PRs for the obvious ones.✓ コピーしました

→ Agent executes task autonomously
Instrument

Enable OTel traces and pipe to Honeycomb/Grafana.✓ コピーしました

→ Spans visible

結果： A production-ready automation agent with observability.

注意点

Agent hallucinates tool calls that don't exist — Restrict the MCP set passed to the agent; fewer, well-documented tools > more
Retries amplify transient upstream issues — Tune retry policy and add exponential backoff

組み合わせ： github · sentry

Compose a multi-agent crew for research tasks

👤 Developers exploring agent patterns ⏱ ~45 min advanced

使うタイミング： A task benefits from specialization (researcher + writer + reviewer).

フロー

Define agents

Create agents: Researcher (web search MCP), Writer (drafts), Reviewer (fact-checks Researcher's sources).✓ コピーしました

→ Three typed agent instances
Delegate

Run the crew: topic 'state of MCP in 2026'. Have Researcher gather, Writer draft, Reviewer verify claims.✓ コピーしました

→ Coordinated output

結果： Higher-quality output than a single-pass agent on complex tasks.

組み合わせ： omnisearch

Build a streaming chatbot with tool access

👤 Product devs integrating AI into a TS app ⏱ ~40 min advanced

使うタイミング： User-facing feature that needs real-time streaming + MCP tool calls.

フロー

Wire streaming

Build a chat endpoint that streams tokens to the client and calls tools mid-stream as the model requests.✓ コピーしました

→ Working streaming endpoint
Explainability

After each response, expose agent.summary() so the UI can show which tools were used.✓ コピーしました

→ Tool trail visible

結果： A production chat UI with transparent tool use.

組み合わせ

他のMCPと組み合わせて10倍の力を

volcano-agent-sdk + github + sentry

Autonomous triage agent across incident + code

Build an agent that, given a Sentry alert, fetches the stack, finds the offending commit via GitHub, and opens a PR with a minimal fix.✓ コピーしました

volcano-agent-sdk + vurb-ts

Vurb builds the server side; Volcano builds the agent side

Expose my business data via a Vurb MCP; build a Volcano agent that uses it to answer user questions.✓ コピーしました

ツール

このMCPが提供する機能

ツール	入力	呼び出すタイミング	コスト
(SDK)	You write TS; SDK picks tools from configured MCPs automatically	N/A — Volcano Agent SDK is a library you build with, not an MCP server you call	n/a — depends on model + tools

コストと制限

運用コスト

APIクォータ: LLM provider limits apply; MCP upstream limits apply
呼び出しあたりのトークン: Depends on model + conversation length
金額: SDK free; LLM usage billed by provider
ヒント: Use cheaper models (Haiku/GPT-4o-mini) for routing and reserve expensive models for reasoning; Volcano supports per-step model choice.

セキュリティ

権限、シークレット、影響範囲

認証情報の保管： LLM provider keys + MCP credentials in env; SDK injects them

データ送信先： LLM provider APIs + configured MCP endpoints

絶対に付与しない： LLM keys to untrusted code paths in the same process

Auto tool selection means the agent can call anything you give it — scope MCP surface narrowly.
OTel traces may include prompt/response content — review before exporting to third-party APM.

トラブルシューティング

よくあるエラーと対処法

MCP connection fails on startup

Verify the MCP endpoint URL and auth. SDK logs full error when --debug is set.

確認： Curl the MCP endpoint directly

Model refuses to use available tools

Tool descriptions may be poorly phrased; rewrite for clarity or force via agent config.

確認： Inspect tools via agent.listTools()

High token cost on simple tasks

Check that system prompt isn't dragging MCP tool defs into every call; use lazy tool-load mode.

確認： agent.summary() shows token breakdown

代替案

volcano-agent-sdk 他との比較

代替案	代わりに使う場面	トレードオフ
LangChain / LangGraph (TS)	You want the largest ecosystem of integrations	Heavier abstraction; slower cold path
Vercel AI SDK	You want tight Next.js integration	Less focus on multi-agent patterns
Anthropic SDK raw	You only need Anthropic and minimal abstraction	You reimplement tool routing, retries, multi-provider

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る