Commander
Commander MCP provides AI assistants with background process management capabilities through PMDaemon integration, enabling execution, monitoring, and control of long-running processes via standard I/O transport. Built by Towry Wang in Rust using the official MCP SDK, it offers seven tools for running commands in the background, killing/stopping processes, reading persistent logs, restarting processes, and listing all managed processes with detailed status information including CPU usage, memory consumption, and uptime. The implementation automatically generates process IDs from command keywords, detects early process failures within one second of startup, and maintains persistent log files that can be accessed at any time, making it valuable for AI assistants that need to manage development servers, build processes, or any long-running background tasks across Linux, macOS, and Windows platforms.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- monitoring
- Source
- PulseMCP
- Repository
- github.com/towry/commander-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Commander 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.