云服务 MCP 服务器

Check what other agents hit the same tool failure — and what recovery worked. Ask before retrying.

MCP server for Duplicacy: backup health, status and Prometheus metrics from duplicacy-exporter

Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.

Agent observability platform that discovers and recommends MCP servers, with GA4, Vercel, GitHub and Sentry connectors and ROI tracking.

Data freshness verification: probe endpoints for cache staleness, latency, content fingerprints, TLS, DNS and redirects, with…

Tickstem developer tools — manage cron jobs and verify emails from your AI coding assistant.

VMware AVI (NSX ALB) load balancer plus AKO Kubernetes ops — 28 MCP tools.

Build and host full-stack web apps and sites on Hatchable, with per-project database, auth, storage, domains and cron.

Capture local agent traces and inspect failures, approvals, and run comparisons.

Governed Docker + Portainer container-host ops: reads, RCA analyses, guarded writes. 38 tools.

Governed TrueNAS SCALE storage ops — 25 MCP tools with audit, budget, undo guards.

Undoable SFTP deploys to shared hosting (cPanel, Plesk, any SFTP host): backs up every file it replaces on the server, restores with one…

Azure + GCP cost management: spending, forecasts, anomalies, budgets, idle resources, and tags.

Manage Spot.io (Spotinst) Ocean clusters, VNGs, Elastigroups, costs, right-sizing and logs across AWS and Azure accounts.

AI agent activity logging and monitoring on the Alog platform: post logs, create articles, manage social interactions and monitor agent…

Monitor cron jobs and recurring work through a project-scoped Watchgoose connection.

Azure Resource Manager inventory & ops for AI agents — governed, confirmation-gated.

Search & edit Grafana dashboards, query datasources (PromQL/LogQL/SQL), inspect alerts.

Keycloak admin for AI agents — realms, users, clients, roles; safe-by-default governance.

Oracle Cloud discovery + Terraform generation for AI agents — read-only, secret-safe.

Local, payload-free AI cost visibility for agents. Query spend by model, route, or tagged work.

Read-only access to on-prem Linux VMs and PostgreSQL over SSH: service health, logs, database state and table schemas, with allowlists and…

Cloud evaluations and reviews for Azure and static AWS CloudFormation (beta). Requires an account.

Hostodo VPS management: VM details, power control, renaming, OS reinstalls, guest-agent commands and artifact uploads, with scoped tokens…

Website uptime monitoring: run checks from 300+ locations, manage monitors, alerts and incidents

Read access to the Langfuse Public API: traces, observations, sessions, scores, prompts, datasets, metrics, models, projects and comments.

Check whether software services are down using live data from their status pages, including incident details.

Read-only kubectl with structured JSON output, hardcoded safe verbs, withheld Secret and ConfigMap values, and one-shot cluster triage and…

Rank log patterns by volume and cost, then compact, tier down or offload the excess over each cap

MCP server for Dynadot domain registrar — domain search, registration, DNS, and transfers

Access the full NebulaBlock API.

Track LLM token costs across Claude, GPT and Gemini, with optimization hints and savings estimates.

Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents.

Safety-first Terraform: confirmation-gated apply/destroy, risk & cost analysis, drift detection

Query your local super-log bench from an AI agent - read-only log tools over the hub.

Deploy HTML folders to vibie.page from Claude / Cursor — one-line install, OAuth, auto-update.

Live status probes plus published uptime and incident history for 280+ APIs and cloud services.

Cookieless web analytics with Gizmo Analytics: framework-aware setup, traffic queries, site summaries, traffic-change explanations and…

Deploy live HTTPS websites in seconds. Instant subdomains or custom .xyz domains via USDC.

Uptime monitoring for websites, APIs, SSL certificates, domain expiry, ping and TCP/UDP ports: manage monitors and view incidents and…

Website monitoring for AI assistants: catches pages that look broken even when the site is up.

Publish, list, update and delete shareable Markdown/HTML pages from your AI assistant.

Real-user Core Web Vitals from the Chrome UX Report (CrUX) API for any origin or URL.

Deploy and manage SnapDeploy apps from your AI assistant: builds, logs, env vars, add-ons, domains.

AI infrastructure cartographer & MCP server: fingerprints, graphs & watches live infra for agents

Governed Ceph mgr ops: HEALTH_WARN RCA, OSD/PG/pool/RBD/CephFS/RGW, 37 tools.

Governed managed-endpoint ops — login-storm & drift analysis, 13 MCP tools with audit/budget/undo.

Governed Kubernetes ops — 55 MCP tools with audit, budget, undo, risk-tier audit labels.

Governed MinIO ops: capacity RCA, exposure audit, ILM, WORM retention, IAM, healing, 48 tools.

Governed network device ops (NAPALM) — 33 MCP tools with audit/undo.

Governed Nutanix Prism Central v4 ops: clusters/VMs/storage/DR/LCM/RCA, ETag-safe, 51 tools.

Governed Traefik + Caddy + HAProxy ops: routes, upstreams, certs, 5xx RCA. 28 tools.

The runtime your agent deploys to — DB, storage, and a public URL in one MCP call.

Kubernetes cluster operations: inspect pods, deployments, services and logs.

Find, quote, rent and stop GPUs on AmpleRun, paid from a USDC or USDT balance on Base. Read-only unless you allow spending; every rental…

Read-only Loggly search and analytics with aggregation-first traffic tools and IP intelligence.

Observability for AI agents: LLM cost, errors and latency across OpenAI, Anthropic, Gemini and Mistral, plus alerts, budget gates, evals…

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

What changed across metrics, logs and traces, and where it started (Grafana, Victoria, New Relic).

Postfix delivery troubleshooting: queue grouped by deferral reason, qshape, mail log stats and traces, SPF/DKIM/DMARC/PTR checks.…