556 Model Context Protocol servers — searchable, rated, ready to install.
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
MCP server for managing Exoscale cloud infrastructure — compute, Kubernetes, DNS, databases, storage
Oracle Cloud discovery + Terraform generation for AI agents — read-only, secret-safe.
Read-only Kubernetes diagnostics: pods, logs, events, workloads, services, PVCs and nodes.
Paid x402 tools: schema-change detection and x402 seller vetting. Interim hostname.
AI product expert answering from live source code, with sources and a verification status.
Google Maps places, reviews, contributor history, photos and posts as JSON. No Google Cloud.
Deploy HTML or dist/ to a live HTTPS URL. No account. Drop, MCP, or CLI.
List, create and deploy your Prefab project templates from any MCP agent.
Manage Percona PostgreSQL + PgBouncer on Kubernetes — safe-by-default access modes and guards.
Search the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Also sends feedback.
Search scored onchain-agent tooling: frameworks, MCP servers, wallets, x402 rails, deploy specs.
Build LumenJS apps, use the Roxyon BaaS, and deploy apps and web projects to Roxyon infrastructure.
Multi-cloud cost, inventory and waste analysis over MCP: AWS, GCP, Cloudflare and OVH.
Build, validate, simulate, and deploy walkerOS event pipelines
A persistent Docker or Fly computer with a Three.js interface and optional live Xfce desktop.
x402 HTTP 402 + MCP paywall: charge USDC per agent call. Self-host via npx or Docker.
New LLM releases daily: which models became deployable, context window, pricing.
Hosts, metrics, Docker and authorized_keys over a macOS terminal's live SSH connections
MCP server with quote and live cryptocurrency price tools, local and cloud-deployed transports.
Cloud cost, inventory and governance on AWS/Azure/GCP. Read-only by default, optional scoped writes
Dispatch and track Alchemist Cloud tickets, watch deploys, read logs, and query your project DB.
Build a working web app from a prompt, then deploy it to a live URL.
Deploy from your terminal, and give an AI coding agent the same abilities over MCP.
POST /mcp