volcano-agent-sdk MCP — Casos de uso, Instalar & Demo en vivo

Por qué usarlo

Características clave

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

Demo en vivo

Cómo se ve en la práctica

volcano-agent-sdk.replay ▶ listo

0/0

Instalar

Elige tu cliente

~/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
    }
  }
}

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

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

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

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

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

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

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: volcano-agent-sdk

Build a coding agent that uses GitHub + Sentry MCPs

👤 TS devs building internal automation ⏱ ~60 min advanced

Cuándo usarlo: You want a programmable agent, not a chat session.

Requisitos previos

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

Flujo

Install + scaffold

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

→ 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.✓ Copiado

→ Agent executes task autonomously
Instrument

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

→ Spans visible

Resultado: A production-ready automation agent with observability.

Errores comunes

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

Combinar con: github · sentry

Compose a multi-agent crew for research tasks

👤 Developers exploring agent patterns ⏱ ~45 min advanced

Cuándo usarlo: A task benefits from specialization (researcher + writer + reviewer).

Flujo

Define agents

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

→ Three typed agent instances
Delegate

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

→ Coordinated output

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

Combinar con: omnisearch

Build a streaming chatbot with tool access

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

Cuándo usarlo: User-facing feature that needs real-time streaming + MCP tool calls.

Flujo

Wire streaming

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

→ Working streaming endpoint
Explainability

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

→ Tool trail visible

Resultado: A production chat UI with transparent tool use.

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

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.✓ Copiado

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.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
(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

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: LLM provider limits apply; MCP upstream limits apply
Tokens por llamada: Depends on model + conversation length
Monetario: SDK free; LLM usage billed by provider
Consejo: Use cheaper models (Haiku/GPT-4o-mini) for routing and reserve expensive models for reasoning; Volcano supports per-step model choice.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: LLM provider keys + MCP credentials in env; SDK injects them

Salida de datos: LLM provider APIs + configured MCP endpoints

No conceder nunca: 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.

Resolución de problemas

Errores comunes y soluciones

MCP connection fails on startup

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

Verificar: 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.

Verificar: 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.

Verificar: agent.summary() shows token breakdown

Alternativas

volcano-agent-sdk vs otros

Alternativa	Cuándo usarla	Contrapartida
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

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills