Container Sandbox
Container-MCP provides a secure, sandboxed environment for executing code, running commands, accessing files, and performing web operations on behalf of large language models. Built by 54rt1n, it implements multiple layers of security including container isolation, AppArmor profiles, Firejail sandboxing, and strict resource limits to ensure safe execution of potentially risky operations. The architecture uses domain-specific managers for different operation types (Bash, Python, file operations, web browsing) and runs inside an Ubuntu container with carefully controlled permissions and access restrictions. This implementation is particularly valuable for AI workflows requiring secure tool execution without exposing the host system to potential risks.
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
- security
- Source
- PulseMCP
- Repository
- github.com/54rt1n/container-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Container 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.