Jetson Nano Management
JetsonMCP server by Ajeet Singh Raina provides AI assistants with complete remote management capabilities for NVIDIA Jetson Nano edge computing systems through SSH connections, offering nine specialized tool categories including hardware control (power modes, thermal management, GPIO), AI workload deployment (CUDA verification, ML framework installation, model optimization with TensorRT), system administration (package management, service control), and container orchestration with GPU acceleration support. Built with Python using paramiko for SSH connectivity and featuring comprehensive error handling, connection pooling, and mock testing capabilities, the implementation enables conversational management of edge AI infrastructure including JetPack SDK management, performance optimization, security hardening, and monitoring workflows. Designed for developers deploying AI applications on Jetson hardware, system administrators managing edge computing fleets, and AI researchers requiring programmatic access to GPU-accelerated inference optimization and thermal management on embedded systems.
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/ajeetraina/jetsonmcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Jetson Nano Management 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.