Agent Workspace
Agent Workspace provides a secure, containerized sandbox where AI agents can autonomously write, test, and execute code. It offers a full project lifecycle with uv for Python dependency management, bash execution with mandatory timeouts, filesystem operations with path-traversal protection, multi-layer security (non-root execution, read-only root filesystem), and atomic file editing with syntax validation for Python, JSON, and TOML. Real-time logging and audit capabilities are included. Designed to prevent AI-driven code execution from affecting the host system.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/hrrodan/agent-workspace-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Agent Workspace 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.