CI、デプロイ、コンテナ、Kubernetes。 5,251 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。
The Runpod plugin's skills, reference docs, golden paths and concept graph as one JSON bundle, for programs such as the Runpod MCP server
Find it. Break it. Fix it. The hacker's toolkit for AI agents.
MCP server for Apple Notes - read, search, create, edit, organize, and export notes on macOS via Claude and other AI assistants
Ditto Memory CLI — save, search, fetch, and traverse the Ditto memory graph from the shell.
A/B testing for agent configuration: paired evaluation of Skills, rules and MCP setups, with deterministic verifiers and replayable evidence.
Test your MCP server the way agents and clients meet it: the menu, the calls, the results, the sign-in, and every release after. No LLM involved.
AgentConnect computer daemon: drives a desktop through Cua Driver and serves the computer_* tools over MCP; installed and upgraded by agentconnect computer
Haven connect — one command wires an AI agent to budgeted, non-custodial payments: installs the MCP runtime and generates the agent signing key locally, registering only the public address.
OAuth/OIDC authentication adapter for MCP clients
MCP server exposing SpecGuard suite intelligence to AI coding agents
Model Context Protocol (MCP) server for Google Sheets API integration
Haven edge signer — holds the agent's delegate key locally and signs payment hashes + x402 headers. Pairs with the hosted, keyless @haven_ai/mcp-server; the key never leaves the machine.
Strict zod schemas + parsers for GGUI marketplace artifact manifests — ggui.gadget.json (gadget bundles) and ggui.blueprint.json (cached UI blueprints).
Local stdio bridge to the Linkbreakers MCP server (https://mcp.linkbreakers.com) for MCP clients that only run local servers.
Build, test, deploy and run AI phone agents: agents, numbers, calls, tests, knowledge, campaigns.
Manage WiseWall sites from an AI coding assistant — deploy, configure DNS, secrets, and plans.
Fast, sandboxed V8 isolate runtime for agent-generated JavaScript. Two-process architecture for crash isolation.
Trust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching.
Command line and stdio MCP server for reading, reviewing, and redlining .docx files with folio: tracked-change edits, comments, and comparisons written atomically with version preconditions.
Auto-starting stdio MCP server that bridges Claude Code to Unreal Engine editors via UE's Python Remote Execution. Launcher per session; singleton HTTP daemon fans in to share the UE connection.
PeerBand CLI and Herdr plugin: reach your local coding agents from any MCP client through your PeerBand account
Secure Kubernetes MCP server: scoped, redacted diagnostics and human-approved writes
Shared configuration, keystore, and SDK factory used by @upshiftfinance/cli and @upshiftfinance/mcp.
Save browser reproductions as State Cards. Reopen them and verify fixes with your coding agent.
Open-source retrieval for agentic RAG: document search with exact citations on your laptop or servers, with OCR, CLI, MCP, and TypeScript.
The wh CLI for WarmHub — create repos, commit and query data, and compound knowledge with your AI agents.
Cost reduction for Codex and Claude Code: focused code context, MCP retrieval, and usage receipts.
Deploy and run apps, databases, domains, storage, email and search on Dbrij from your AI assistant.
MCP server for CodeSpar — give Claude, Codex, Cursor & ChatGPT a commerce agent (pay, charge, wallet, mandates, Pomelo card) over MCP
Unofficial pi package that exposes Z.ai MCP server tools for web search, URL reading, repository reading, and vision workflows.
Give agents every interface—install once to search, run, inspect, and repair real software across APIs, browsers, desktops, local tools, and MCP.
botnote CLI and MCP server. Talk to a botnote daemon from the terminal or from any MCP client.
From web terminals for your coding agents to a self-running agent company: Claude Code and Codex in parallel git worktrees, a job board they pick work from, and one agent that runs the board from a go
Headless maind CLI — pull stack-relevant lessons into CI runners, report CI outcomes, brief agents on local git state (branch, PRs, peers), and launch coding agents behind a local NVIDIA NeMo Switchya
The deterministic, verifiable grounding layer for AI code work. Flags fabricated files, imports and symbols in AI answers against your repo and installed libraries. Zero dependencies, offline, byte-st
Jarela — local chat interface for LangGraph agents (multi-provider, single-process, SQLite-backed).