MCP Process Server
A Model Context Protocol (MCP) server that provides process management and monitoring capabilities for AI agents, with strict security boundaries enforced by executable allowlists.
🔗 Repository
This package is now maintained in its own repository: https://github.com/Digital-Defiance/mcp-process
This repository is part of the [https://github.com/Digital-Defiance/ai-capabilitites-suite](AI Capabilitites Suite) on GitHub.
Features
Process Launching: Spawn processes with specified arguments and environment
Resource Monitoring: Track CPU, memory, and I/O usage
Output Capture: Capture stdout and stderr streams
Process Termination: Graceful and forced termination
Service Management: Long-running services with auto-restart
Process Groups: Manage related processes and pipelines
Security: Multi-layer security with executable allowlists
Security
This server implements defense-in-depth security:
Executable Allowlist: Only pre-approved executables can be launched
Argument Validation: Command arguments validated for injection attacks
Environment Sanitization: Dangerous environment variables removed
Resource Limits: CPU, memory, and time limits prevent resource exhaustion
Privilege Prevention: No privilege escalation or setuid executables
Audit Logging: Complete operation tracking
Installation
Development
License
MIT