volcano-agent-sdk MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

volcano-agent-sdk.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

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

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

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

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

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

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: volcano-agent-sdk

Build a coding agent that uses GitHub + Sentry MCPs

👤 TS devs building internal automation ⏱ ~60 min advanced

언제 쓸까: You want a programmable agent, not a chat session.

사전 조건

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

흐름

Install + scaffold

npm install @volcano.dev/agent and write a minimal agent that connects to github + sentry MCPs with Anthropic as the model.✓ 복사됨

→ 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.✓ 복사됨

→ Agent executes task autonomously
Instrument

Enable OTel traces and pipe to Honeycomb/Grafana.✓ 복사됨

→ Spans visible

결과: A production-ready automation agent with observability.

함정

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

함께 쓰기: github · sentry

Compose a multi-agent crew for research tasks

👤 Developers exploring agent patterns ⏱ ~45 min advanced

언제 쓸까: A task benefits from specialization (researcher + writer + reviewer).

흐름

Define agents

Create agents: Researcher (web search MCP), Writer (drafts), Reviewer (fact-checks Researcher's sources).✓ 복사됨

→ Three typed agent instances
Delegate

Run the crew: topic 'state of MCP in 2026'. Have Researcher gather, Writer draft, Reviewer verify claims.✓ 복사됨

→ Coordinated output

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

함께 쓰기: omnisearch

Build a streaming chatbot with tool access

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

언제 쓸까: User-facing feature that needs real-time streaming + MCP tool calls.

흐름

Wire streaming

Build a chat endpoint that streams tokens to the client and calls tools mid-stream as the model requests.✓ 복사됨

→ Working streaming endpoint
Explainability

After each response, expose agent.summary() so the UI can show which tools were used.✓ 복사됨

→ Tool trail visible

결과: A production chat UI with transparent tool use.

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨

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.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
(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

비용 및 제한

운영 비용

API 쿼터: LLM provider limits apply; MCP upstream limits apply
호출당 토큰: Depends on model + conversation length
금액: SDK free; LLM usage billed by provider
팁: Use cheaper models (Haiku/GPT-4o-mini) for routing and reserve expensive models for reasoning; Volcano supports per-step model choice.

보안

권한, 시크릿, 파급범위

자격 증명 저장: LLM provider keys + MCP credentials in env; SDK injects them

데이터 외부 송신: LLM provider APIs + configured MCP endpoints

절대 부여 금지: 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.

문제 해결

자주 발생하는 오류와 해결

MCP connection fails on startup

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

확인: 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.

확인: 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.

확인: agent.summary() shows token breakdown

대안

volcano-agent-sdk 다른 것과 비교

대안	언제 쓰나	단점/장점
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

volcano-agent-sdk