AI-powered self healing infrastructure MCP server for agents. Supports node health check, cl...
Self MCP server exists for a simple reason — assistants are far more useful when they can act on Self directly instead of describing what you should do. AI-powered self healing infrastructure MCP server for agents. Supports node health check, cl...
Every tool call goes through the Sovereign Governance Layer:
Once Self is connected, these are the calls the assistant has available:
node_health_check — Check CPU, memory, disk, GPUcluster_health_check — Check all 9 nodesrestart_service — Restart failed serviceauto_remediate — Fix common issuesgpu_orchestration — Allocate GPU across clusterfailover_decision — Determine failover actioncost_report — Infrastructure cost breakdowncompliance_check — Check if issue is auto-remediablecouncil_propose — Propose critical action to BFT Councilcouncil_vote — Cast vote on pending proposalcouncil_status — Check proposal statusverify_attestation — Verify Ed25519 sigil on any action@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Self's toolset — node_health_check, cluster_health_check, restart_service and 9 more — is a fair guide to whether it matches your workflow. It is maintained by CSOAI-ORG; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| node_health_check | Check CPU, memory, disk, GPU |
| cluster_health_check | Check all 9 nodes |
| restart_service | Restart failed service |
| auto_remediate | Fix common issues |
| gpu_orchestration | Allocate GPU across cluster |
| failover_decision | Determine failover action |
| cost_report | Infrastructure cost breakdown |
| compliance_check | Check if issue is auto-remediable |
| council_propose | Propose critical action to BFT Council |
| council_vote | Cast vote on pending proposal |
| council_status | Check proposal status |
| verify_attestation | Verify Ed25519 sigil on any action |
{
"mcpServers": {
"self-healing-infrastructure": {
"command": "npx",
"args": ["-y", "@smithery/cli"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.