Agent VM
Agent VM provides a Docker-based sandboxed Linux environment with filesystem and shell access exposed through a standard MCP Streamable HTTP interface. The embedded resolver offers file listing, reading with automatic chunking for large files, writing with auto-created parent directories, and shell command execution with real-time SSE streaming of output. Security is enforced through seven independent layers including configurable security modes (strict, moderate, permissive), command whitelisting and blacklisting, argument validation, direct execution without shell interpretation, and comprehensive audit logging.
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/sean-lai-sh/agent-vm
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Agent VM 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.