Code Sandbox
This MCP server provides AI assistants with secure code execution capabilities across 7 programming languages (Python, JavaScript, TypeScript, Ruby, Bash, Zsh, Fish) through Docker containerization with strict security controls. Built using Ruby 3.4 with Alpine Linux for minimal attack surface, the implementation features multi-stage Docker builds, real-time output streaming, syntax validation tools, and comprehensive security measures including read-only filesystems, network isolation, resource limits, and non-root execution. Serves developers needing safe code execution environments for AI workflows, educational platforms requiring sandboxed programming environments, and teams building AI-powered development tools that need reliable code execution with proper isolation and security controls.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · 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/timlikesai/code-sandbox-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Code 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.