Add Resource Limits for MCP Instances to Prevent CPU/Memory Exhaustion (WSL2 - Workaround)

[aiob3]

MCP Resource Limits Configuration Proposal

Description:

Problem Statement

Docker MCP Gateway / cagent currently has no built-in mechanism to limit:

• Maximum concurrent MCP instances running in parallel
• Memory per instance
• Total memory consumption
• CPU allocation per tool
• Instance lifecycle (timeout, cleanup)

This leads to resource exhaustion on local development machines (especially WSL 2), causing:

• 90%+ CPU usage from uncontrolled docker-mcp.exe spawning
• Memory bloat
• System lockups
• Daemon crashes

Issue

Example of Current Issue - Suggest Improve

• Workaround Complete
  MCP_RESOURCE_LIMITS_PROPOSAL.md

• MCP-concurrent-limits
  .mcp-limits.yaml
  MCP_RESOURCE_LIMITS_PROPOSAL.md

Affected Users:

• Local development with multiple MCP tools
• WSL 2 environments with limited resources
• Docker Desktop users

Workaround (Current):
Manual task killing: taskkill /F /IM docker-mcp.exe

Expected Behavior:
MCP should respect configurable per-tool and global resource limits

[aiob3]

@claude you can help us?