Qwen
Enables AI assistants to leverage Qwen's code analysis capabilities with large context windows, supporting file/directory analysis, sandbox execution, and multiple approval modes for safe code operations.
What is Qwen?
Qwen is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to leverage qwen's code analysis capabilities with large context windows, supporting file/directory analysis, sandbox execution, and multiple approval modes for safe code operati...
Enables AI assistants to leverage Qwen's code analysis capabilities with large context windows, supporting file/directory analysis, sandbox execution, and multiple approval modes for safe code operations.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI assistants to leverage Qwen's code analysis capab
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx qwen-mcp-toolConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Qwen
The Qwen MCP Tool is a TypeScript-based MCP server that bridges MCP-compatible AI assistants (such as Claude) with the Qwen CLI, allowing them to delegate tasks to Qwen's large-context-window models for deep code analysis, file and directory inspection, and sandboxed code execution. It exposes an ask-qwen tool that accepts natural language prompts with @filename and @directory file references, supports multiple Qwen models (qwen3-coder-plus, qwen3-coder-turbo), and offers configurable approval modes from interactive to fully automated. This enables AI agents to collaborate with a second specialized model for tasks requiring larger context than the primary model can handle.
Prerequisites
- Node.js v16 or higher installed
- Qwen CLI installed and configured — install from github.com/QwenLM/qwen-code and authenticate with your Alibaba Cloud/Qwen API credentials
- An MCP client such as Claude Desktop or Claude Code
- npm or npx available in your PATH
Install the Qwen CLI
Before using the MCP tool, install and configure the Qwen CLI from QwenLM. Follow its setup guide to authenticate with your API credentials.
npm install -g @qwen-ai/qwen-code
# Follow the qwen-code setup to authenticateAdd the server via Claude Code (easiest method)
If you are using Claude Code, add the Qwen MCP tool with a single command. This configures everything automatically.
claude mcp add qwen-cli -- npx -y @jaggerxtrm/qwen-mcp-toolInstall globally via npm (alternative)
For Claude Desktop or other MCP clients, install the package globally.
npm install -g @jaggerxtrm/qwen-mcp-toolConfigure Claude Desktop
Add the server to your Claude Desktop config at ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) using npx for zero-install execution.
{
"mcpServers": {
"qwen-cli": {
"command": "npx",
"args": ["-y", "@jaggerxtrm/qwen-mcp-tool"]
}
}
}Restart your MCP client and test
Restart Claude Desktop or Claude Code. The ask-qwen, ping, and help tools should now be available. Send a ping to verify the connection.
Qwen Examples
Client configuration
Claude Desktop configuration using npx for the Qwen MCP Tool. No environment variables are required beyond the Qwen CLI being configured.
{
"mcpServers": {
"qwen-cli": {
"command": "npx",
"args": ["-y", "@jaggerxtrm/qwen-mcp-tool"]
}
}
}Prompts to try
Example prompts demonstrating file analysis, codebase summarization, and sandboxed execution via Qwen.
- "Use Qwen to analyze @src/main.ts and explain what it does"
- "Ask Qwen to summarize the architecture of @src/ using qwen3-coder-plus"
- "Have Qwen run the test suite and fix any failures (use sandbox mode)"
- "Use Qwen to analyze the entire @. codebase and identify security vulnerabilities"
- "Ask Qwen to refactor @utils/helpers.ts with auto-edit approval mode"Troubleshooting Qwen
ask-qwen tool returns 'Qwen CLI not found' or command not found errors
Ensure the Qwen CLI (qwen-code) is installed and accessible in your PATH. Run 'which qwen' or 'qwen --version' in your terminal to verify. If installed globally via npm, restart your terminal session to refresh the PATH.
Quota limit errors causing fallback to qwen3-coder-turbo
This is expected behavior — the tool automatically falls back to qwen3-coder-turbo when qwen3-coder-plus hits rate limits. To force a specific model, pass it explicitly in your prompt: 'Use Qwen with model qwen3-coder-turbo to...'.
File references with @filename are not being included
Ensure @filename paths are relative to the current working directory where the MCP server process is running. For directories, use @dirname/ with a trailing slash. Absolute paths are also supported.
Frequently Asked Questions about Qwen
What is Qwen?
Qwen is a Model Context Protocol (MCP) server that enables ai assistants to leverage qwen's code analysis capabilities with large context windows, supporting file/directory analysis, sandbox execution, and multiple approval modes for safe code operations. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Qwen?
Follow the installation instructions on the Qwen GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Qwen?
Qwen works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Qwen free to use?
Yes, Qwen is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Qwen Alternatives — Similar Coding Agents Servers
Looking for alternatives to Qwen? 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 Qwen 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 Qwen?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.