Docker Code Runner
This code execution server enables AI assistants to run Python and bash code in isolated Docker containers or virtual machines, providing a secure sandboxed environment for code execution tasks. Built with FastMCP and Docker integration, it supports both ephemeral containers (created from images) and persistent named containers, with configurable timeouts and environment variables. The implementation includes a Kali Linux-based container with pre-installed security tools and scientific packages, making it particularly useful for cybersecurity analysis, data science workflows, and general-purpose code execution where isolation and security are paramount.
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 2026-09-01.
Scan details: Circle-IR · 2026-09-01 · 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/whh4git/mcp-code-runner
- Author type
- human
- Last scanned
- 2026-09-01
- Updated
- 2026-09-01
Use via MCP
Resolve Docker Code Runner 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.