cal/claude-home
1
0
Fork 0
Code Issues 6 Pull Requests 4 Actions Packages Projects Releases Wiki Activity

docs: remove decommissioned MCP Gateway (CT 303) from monitoring inventory

Browse Source 
Migrated MCP servers back to local stdio config, shut down LXC 303.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Cal Corum 2026-02-25 12:39:53 -06:00
parent df553e5142
commit 5ff94a9d20
1 changed files with 1 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
monitoring/CONTEXT.md
View File

@ -14,7 +14,7 @@ Comprehensive monitoring and alerting system for home lab infrastructure with fo
- **Network Monitoring**: Connectivity and service availability
- **Container Monitoring**: Docker/Podman health and resource usage
### AI Infrastructure LXCs (301–303)
### AI Infrastructure LXCs (301–302)
#### Claude Discord Coordinator — CT 301 (10.10.0.147)
**Purpose**: Discord bot coordination with read-only cognitive memory MCP access
@ -25,14 +25,6 @@ Comprehensive monitoring and alerting system for home lab infrastructure with fo
**Repo**: `cal/claude-runner-monitoring` on Gitea (cloned to `/root/.claude` on CT 302)
**Docs**: `monitoring/server-diagnostics/CONTEXT.md`
#### MCP Gateway — CT 303 (10.10.0.231)
**Purpose**: Docker MCP Gateway — centralized MCP server proxy for Claude Code
**SSH alias**: `mcp-gateway`
**Service**: `docker/mcp-gateway` v2.0.1 on port 8811 (`http://10.10.0.231:8811/mcp`)
**MCP servers**: n8n (23 tools, connects to LXC 210), Gitea (109 tools, connects to git.manticorum.com)
**Config**: `/home/cal/mcp-gateway/` — `secrets.env`, `config/config.yaml`, `config/registry.yaml`, `gitea-catalog.yaml`
**Note**: Uses `--servers` flag for static server activation (Docker Desktop secret store unavailable on headless Engine). Custom catalog adds Gitea MCP via `docker.gitea.com/gitea-mcp-server` image.
**Two-tier system:**
- **Tier 1** (`health_check.py`): Pure Python, runs every 5 min via n8n. Checks containers, systemd services, disk/memory/load. Auto-restarts containers when allowed. Exit 0=healthy, 1=auto-fixed, 2=needs Claude.
- **Tier 2** (`client.py`): Full diagnostic toolkit used by Claude during escalation sessions.