Sandbox Fusion
The Sandbox Fusion MCP server provides AI assistants with access to the Sandbox Fusion environment through a Python-based implementation. Built using the MCP and Sandbox Fusion packages, this server runs in a dedicated Conda environment and handles communication between AI models and the sandbox environment. The implementation includes a simple launch script for environment activation and server startup, making it easy to deploy for developers working with AI agents that need to interact with simulated environments for testing, training, or demonstration purposes.
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
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/astricaelus/sandbox-fusion-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Sandbox Fusion 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.