Docker Sandbox
This sandbox MCP server provides isolated Docker environments for executing code in multiple programming languages. It integrates with Claude Desktop and allows creating containers, writing and running code, installing packages, and setting up development environments. The implementation stands out by offering persistent containers, state saving, and Dockerfile generation for reproducible setups. Built with Python using the MCP and Docker libraries, it's particularly useful for AI assistants or applications needing to run untrusted code, test software in isolated environments, or provide interactive coding capabilities. Use cases include automated code testing, providing a secure coding playground, or enabling AI systems to write and execute code on demand.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/tsuchijo/sandbox-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Docker Sandbox from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.