Skip to main content
MCPAgent from @mcp-use/agent connects a model to MCP tools, runs a bounded tool-calling loop, and returns the model’s final answer.

Install the agent

@mcp-use/agent requires Node.js 22.22.2 or later.

Run your first agent

Set OPENAI_API_KEY, then run this example from a directory the filesystem server may read.
A successful run prints a text answer based on the files the MCP server returned.
Initialization is manual by default. Call await agent.initialize() before run(), stream(), or streamEvents(). Set autoInitialize: true only when you want the first call to initialize the agent for you.

Understand the runtime defaults

maxSteps defaults to 10. Override it for the agent or for one call:
Conversation memory is enabled by default. Memory stores the user prompt and final assistant text from successful run() and stream() calls. It does not store tool transcripts or streamEvents() output. When you pass mcpServers, the agent creates and owns its MCPClient; close() closes those sessions. If you pass an existing client or connectors, their lifecycle remains under your control.

Choose the next guide

LLM providers

Configure OpenAI, Anthropic, Google, OpenRouter, Ollama, or an OpenAI-compatible endpoint.

Memory management

Inspect, disable, and clear conversation history.

Streaming

Stream tool steps or provider-neutral events.

LangChain integration

Add LangChain models, structured output, Server Manager, and callbacks.