Volcano Agent SDK
🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.
What is Volcano Agent SDK?
Volcano Agent SDK is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🌋 build ai agents that seamlessly combine llm reasoning with real-world actions via mcp tools — in just a few lines of typescript.
🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🌋 Build AI agents that seamlessly combine LLM reasoning with
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx volcano-agent-sdkConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Volcano Agent SDK
Volcano Agent SDK is a TypeScript-first framework from Kong that lets you build AI agents capable of combining LLM reasoning with real-world actions through MCP tools in just a few lines of code. It supports multiple LLM providers (OpenAI, Anthropic, Mistral, Bedrock, Vertex, Azure) and enables both single-agent and multi-agent coordination patterns with parallel execution, streaming, and OpenTelemetry observability built in. Developers use it to wire up MCP servers as agent tools without boilerplate, composing workflows that span multiple specialized agents.
Prerequisites
- Node.js 18+ and npm or yarn
- An API key for your chosen LLM provider (e.g., OPENAI_API_KEY or Anthropic API key)
- One or more MCP servers running and accessible (HTTP or stdio)
- TypeScript knowledge recommended for full type-safe usage
Install the SDK
Install the Volcano Agent SDK package from npm. This brings in MCP client support and LLM provider adapters without additional peer dependencies.
npm install @volcano.dev/agentSet your provider API key
Export the API key for your chosen LLM provider as an environment variable. The SDK reads standard provider env vars.
export OPENAI_API_KEY=your-openai-api-key
# or for Anthropic:
export ANTHROPIC_API_KEY=your-anthropic-api-keyDefine your LLM and MCP tool sources
Import the SDK and declare your LLM provider and MCP server URLs. The mcp() helper connects to any HTTP MCP endpoint and makes its tools available to agents.
import { agent, llmOpenAI, mcp } from '@volcano.dev/agent';
const llm = llmOpenAI({ apiKey: process.env.OPENAI_API_KEY, model: 'gpt-4o-mini' });
const weatherTools = mcp('http://localhost:8001/mcp');
const taskTools = mcp('http://localhost:8002/mcp');Run a single agent with tool access
Create an agent, pass it a prompt and the MCP tool sources, then call run(). The LLM automatically selects which tools to invoke based on the prompt and loops until the task is complete.
const result = await agent({ llm })
.then({
prompt: "What's the weather in Seattle? If it will rain, create a task to bring an umbrella.",
mcps: [weatherTools, taskTools]
})
.run();
console.log(result);Build a multi-agent coordination pattern
Define specialized agents with roles and descriptions, then create a coordinator agent that delegates to them. The coordinator decides which sub-agent handles each subtask autonomously.
const researchAgent = agent({ llm, description: 'Researches topics using web search tools' });
const writerAgent = agent({ llm, description: 'Writes polished content from research notes' });
const coordinator = agent({ llm });
const report = await coordinator
.then({ prompt: 'Write a report on AI trends', agents: [researchAgent, writerAgent] })
.run();Volcano Agent SDK Examples
Client configuration
Volcano Agent SDK is a code library, not a standalone MCP server — configure it in your TypeScript project. Here is a minimal working agent that connects two MCP servers.
{
"mcpServers": {
"volcano-agent": {
"command": "npx",
"args": ["volcano-agent-sdk"]
}
}
}Prompts to try
When using agents built with Volcano SDK, these are example task prompts that demonstrate multi-tool and multi-agent capabilities.
- "Search for recent news on quantum computing and summarize the top 3 stories"
- "Check the weather in New York and if it's below 40°F, add a task to wear a coat"
- "Analyze the files in ./src, find any TODO comments, and create GitHub issues for each"
- "Fetch our Slack messages from today and draft a daily standup summary"
- "Run the test suite, collect failures, and open pull requests with proposed fixes"Troubleshooting Volcano Agent SDK
MCP server connection fails with ECONNREFUSED
Ensure the MCP server process is running before the agent starts. The mcp() helper connects at runtime — start your MCP server first, then run the agent script.
Agent loops indefinitely without completing the task
Set a maxIterations or timeout option on the agent to cap the tool-calling loop. Also ensure your MCP tools return clear completion signals rather than partial results that prompt further tool calls.
TypeScript compilation errors for missing types
Ensure you have TypeScript 5.0+ and that tsconfig.json sets moduleResolution to 'bundler' or 'node16'. The SDK ships full type declarations but requires a modern module resolution mode.
Frequently Asked Questions about Volcano Agent SDK
What is Volcano Agent SDK?
Volcano Agent SDK is a Model Context Protocol (MCP) server that 🌋 build ai agents that seamlessly combine llm reasoning with real-world actions via mcp tools — in just a few lines of typescript. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Volcano Agent SDK?
Follow the installation instructions on the Volcano Agent SDK GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Volcano Agent SDK?
Volcano Agent SDK works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Volcano Agent SDK free to use?
Yes, Volcano Agent SDK is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Volcano Agent SDK Alternatives — Similar Coding Agents Servers
Looking for alternatives to Volcano Agent SDK? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Volcano Agent SDK in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Volcano Agent SDK?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.