CI、デプロイ、コンテナ、Kubernetes。 5,250 件のサーバーを利用の多い順に掲載しています。それぞれ公開元のページが開きます。
Teamtrail: the trail map for your AI coding agents. You pick the destination, your agents walk the trail, and you only get the calls that need you.
MCP server for PostgreSQL: local, Docker, RDS, Neon, Supabase, or behind an SSH bastion.
Model Context Protocol server for the Keel GRC API: drive your compliance program from Claude, Cursor, or any MCP client.
Pinned MCP wire types, protocol versions, and upstream provenance for Toolgrain.
SvelteKit adapter: typed content reads and endpoint mounts over Graft's stateless handlers.
Helm charts and cloud native packages from Artifact Hub. No key required.
Reviewable company, ETF and index research for Codex, Claude Code, OpenCode, Grok Build and ChatGPT Work developer mode: sourced evidence, method lenses, debate and PM synthesis.
Atlarix CLI: an AI coding agent in your terminal. Works with any model (Atlarix Auto, your own API key, or a local model) and runs unattended with `atlarix run` for CI.
Prebuilt Levelrail CLI binary for windows/arm64. Installed automatically by levelrail-cli, do not install directly.
Control AWX/Ansible Tower through natural language - 49 tools for automation
Compare, estimate, and deploy cloud infrastructure across AWS, GCP, and Azure for AI agents.
Milestones, handoff tickets, project context, and deploy signals for AI-built apps over MCP.
Create xmcp apps with one command
Model Context Protocol (MCP) server dispatcher for ServerKit.
Infrastructure management CLI — deploy automation, health checks, and MCP bridge
Share skills and shells across your machines through one MCP endpoint.
MCP server, dev tools, and the action-to-tool projection — one authz system, two surfaces
日本語対応のConoHa VPS Model Context Protocol (MCP) サーバー
Extension manager for AI coding agents — install skills, subagents, MCP servers, rules, hooks, knowledge, and packs across Claude Code, Codex, Cursor, Copilot, and more.
Deploy and run apps, workers, jobs, Postgres, and Valkey on Ownkube from your coding agent.
AI inference for your coding agents. Route models, control spending, and fund your workspace.
TypeScript SDK、核心的預編譯二進位綁定與命令列工具,三者為同一次發布產出
Auto Runtime runs the playbooks your agent builds: their reasoning, lookup, memory, interaction, prediction and computation functions, and the workflows that coordinate them.
Talk with Claude out loud on your Mac: speaks with macOS `say`, listens for one natural conversational turn, and transcribes on-device with whisper.cpp. An MCP server.
Cross-platform CLI tool for Unreal-MCP (Skills & MCP). Resolves and launches the Unreal editor with MCP connection env vars, runs MCP/system tools over HTTP, probes server health, configures AI agents
Local MCP server that gives any AI agent safe cross-OS desktop control — the fallback execution layer for when APIs, CLIs, and direct integrations aren't available. Works with any tool-calling model (
MCP server for the Flyle AI Operator public API
Pre-action gate: verify before pay/trade/write/deploy. execute=true only on ALLOW.
See why your Windows drive is full and free space in ways you can undo: developer and AI tool caches, models, Docker and WSL. Also an MCP server for AI assistants.
Typed TypeScript client for Polaris for PHP, generated from the route manifest
Channel-agnostic PatrolTech agent capabilities (reads, proposed actions and domain helpers) on top of the public PatrolTech SDK, for chat bots and MCP servers
The effected tool's shared logic, consumed by its CLI and MCP front ends
Governed Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations.
Persistent engineering memory for coding agents: plugin and MCP setup for Claude Code, Codex, Grok and Antigravity
QA after every deploy: walks your live web app as a real user and tells your agent what broke.
Peer messaging between live Claude Code, Codex and opencode sessions on the same machine. One MCP server, run inside each.