Promote Sign in Sign up

Agent

mcp-use

Open-source platform for building and deploying AI agents and MCP servers.

Source rating 5.0 (74) 5.1k views 5.1k/mo traffic 0 saves Unknown
AI Agents DEVELOPER TOOLS Cloud infrastructure
More categories (9)
open-source LLM API integration MCP Servers AI development Agent Framework Model Context Protocol Devops Backend development
Visit website Sign in to save

Verdict

A quick read before you dig into the full page.

Best if
You are dev teams and need: Building and deploying custom AI agents with ease
Pick this when
Open-source platform for building and deploying AI agents and MCP servers

Overview

mcp-use is an open-source platform that provides devtools and cloud infrastructure to help development teams quickly build and deploy custom AI agents using MCP (Model Context Protocol) servers. It offers an SDK for creating AI agents, a registry for discovering community-built servers, and a managed gateway for routing, authenticating, and load-balancing MCP servers. The platform aims to simplify the process of building, discovering, and deploying MCP servers and AI agents, supporting various deployment environments including cloud, local VMs, and third-party services.

mcp-use screenshot

Best for

Short scenarios where mcp-use tends to shine.

  • Building and deploying custom AI agents with ease

    Best for Dev teams

  • Spinning up and aggregating MCP servers through a single endpoint

    Best for Engineers

  • Connecting to remote server pools for AI agent operations

    Best for AI product developers

  • Creating AI products (e.g., with Claude, ChatGPT) using MCP clients

    Best for Developers building with MCP

  • Managing all MCP infrastructure from a centralized control plane

    Best for Dev teams

Example outputs 1

Sample generations and before/after results for mcp-use.

mcp-use screenshot
mcp-use screenshot

Access & connections

Where you can use mcp-use, and what it plugs into.

Platforms

Web

Integrations

MCP

Capabilities

What this tool accepts, produces, and is strongest at.

Highlights

  • Open-source SDK for building custom AI agents
  • Cloud infrastructure for deploying and managing MCP servers
  • Managed MCP Gateway for routing, authentication, and load balancing
  • Registry for discovering community-built MCP servers
  • Support for various deployment options (cloud, VM, third-party)

People also view

Tools that often show up alongside mcp-use in collections and comparisons.

In the news

Launch coverage and community mentions for mcp-use.

FAQ 7

What is mcp-use?
mcp-use is an open-source platform that provides devtools and cloud infrastructure to help development teams quickly build and deploy custom AI agents using MCP (Model Context Protocol) servers. It offers an SDK for creating AI agents, a registry for discovering community-built servers, and a managed gateway for routing, authenticating, and load-balancing MCP servers. The platform aims to simplify the process of building, discovering, and deploying MCP servers and AI agents, supporting various deployment environments including cloud, local VMs, and third-party services.
How to use mcp-use?
Users can get started by installing the mcp-use SDK via `pip install mcp-use` or `npm install mcp-use`. With the SDK, developers can create AI agents by connecting to MCP servers, using any model provider (e.g., Claude). The platform allows spinning up and aggregating MCP servers through a single endpoint. Users can deploy fully managed MCP servers in the mcp-use cloud, sandbox local VMs, or proxy third-party servers behind the gateway, all managed from a single dashboard. An AI-powered chat interface is also available for instant testing and interaction with MCP agents.
What is mcp-use?
mcp-use is an open-source platform providing devtools and cloud infrastructure to help dev teams quickly build and deploy custom AI agents with MCP (Model Context Protocol) servers.
What is the mcp-use SDK?
The mcp-use SDK is an open-source library that allows developers to turn any MCP call into an AI agent. It has over 5,000 GitHub stars and 100k downloads, trusted by engineers at NASA, Cisco, NVIDIA, etc.
What is the MCP Gateway?
The managed MCP gateway routes, authenticates, and load-balances all your MCP servers through a single endpoint. It offers built-in OAuth, ACLs, metrics, and tracing for production-grade observability.
Can I deploy my own MCP servers with mcp-use?
Yes, you can deploy fully managed MCP servers in the mcp-use cloud, sandbox local VMs on demand, or proxy third-party servers behind the gateway, all managed in one dashboard.
How can I get support or connect with the mcp-use community?
You can join their Discord community for developers building with MCP and mcp-use, or follow them on social media like Github, LinkedIn, and X.
mcp-use
Visit website