container-use
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
Container-use is an MCP server that provisions isolated containerized development environments for AI coding agents. Built by Dagger, it enables multiple agents to work simultaneously in separate containers and git branches without conflicts or interference. Developers can monitor agent activity in real-time, intervene when needed, and manage each agent's workspace using standard git operations. The server works with any MCP-compatible client including Claude Code, Cursor, and VSCode extensions.
Key Features
Use Cases
- 01Running multiple coding agents simultaneously on different features or experiments
- 02Safely testing AI-generated code changes in isolated environments before merging
- 03Debugging agent behavior by inspecting complete command history and logs
- 04Prototyping with different tech stacks without polluting the main workspace
- 05Training or evaluating coding agents with reproducible containerized setups
- 06Collaborating with AI assistants on multiple parallel tasks without conflicts
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
container-use — FAQ
What is container-use MCP server?+
Container-use is an MCP server that creates isolated containerized development environments for AI coding agents. It allows multiple agents to work in parallel using separate containers and git branches, preventing conflicts and enabling safe experimentation.
How do I install container-use?+
On macOS, use Homebrew: brew install dagger/tap/container-use. For all platforms, run the installation script: curl -fsSL https://raw.githubusercontent.com/dagger/container-use/main/install.sh | bash. Then add it as an MCP server to your AI client.
Which AI clients work with container-use?+
Container-use works with any MCP-compatible client including Claude Code, Cursor, Goose, and VSCode extensions. Setup is consistent across clients: add 'container-use stdio' as an MCP server in your client's configuration.
Does container-use require API keys or prerequisites?+
Container-use requires Dagger to be installed (handled automatically via the installation script). No API keys are needed. You'll need git for branch-based workspace management and a repository where you want agents to work.
Is container-use free to use?+
Yes, container-use is open-source software released under the Apache 2.0 license and free to use. The project is actively developed by Dagger and currently in early experimental stages.
Can I see what agents are doing in their containers?+
Yes, container-use provides real-time visibility into complete command history and logs of all agent operations. You can also drop into any agent's terminal directly to inspect their state or take manual control when needed.
How do I install container-use?+
Open the source repository on GitHub and follow its README. container-use is a mcp server — MCP Agents Market links you directly to the official repo.
Is container-use free?+
container-use is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.