- Conduid
- Marketplace
- #ai-agent
MCP servers tagged ai-agent
4.2K live MCP servers tagged "ai-agent", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ai-agent.
Brockleyai
Build, deploy, and scale production AI agents with typed workflows, durable execution, and integrated infrastructure management.
Mas Sentry Toolkit
Offensive-security scanner for multi-agent systems: MCP and A2A agent protocols plus MQTT agent messaging, verified against the reference SDKs. Aligned with OWASP Agentic Top 10 (…
ARADHYA
Local-first AI Operating Intelligence for Windows — ReAct agent loop, 50+ tools across 15 categories, zero-code Markdown skills framework, and a Hooks→Permissions→Approval safety…
Template LLM Network Agent
Reference architecture: LangGraph agent + MCP tools + Nornir + RAG + guardrails for network operations
Agentfiles Legacy
Discover, understand, and manage your AI agent workflows — GUI for ~/.claude/, ~/.codex/, and project configs
Revit AI Powered Plugin Template
A professional, multi-version, AI-ready Revit add-in template for building production-grade Revit plugins with clean architecture, WPF/WebView2 UI, MCP integration, AI gateway orc…
Kanban Tool
A Rust-based kanban board system designed for coding agents, with a CLI, a terminal UI (TUI), a WebUI, and an MCP server.
Buywhere Cursor Plugin
BuyWhere MCP Tools for Cursor AI — product search, price comparison, and deals for AI agents
Cubelife Example Claude
Example: Claude API agent with a CubeLife pixel-art character
Po Handoff
“Seamless context handoff for Product Owners switching between Cursor, Claude, Gemini & more. Never lose your PRD, user stories, ACs, risks again.”
Agenthusk
Local-first forensic scanner for secrets and risky residue left by AI coding agents.
Agent Learn Skill
LLM & Agent 知识学习、自适应考试和学习路径推荐 Skill 插件 —— 支持 MCP 增强模式与纯本地降级模式
Yandex Market API
Claude/Agent Skill: Yandex Market Partner API — full official OpenAPI spec (159 ops) with lookup CLI
Nilux
AI coding agent that lives in your terminal
Newt Agent
NewtSpeak / Discord 风格服管 CLI：OAuth 登录、频道角色成员治理；MCP 对接 AI（Cursor 等）自动化运维
Kimi Code Plugin
Open Accountants for Kimi Code CLI. Global tax and accounting knowledge built with accountants around the world, with official sources and transparent review status.
Taskpilot
Local-first desktop task & calendar manager built to treat an AI agent as a first-class operator. MCP server, HTTP API, permissions model, agent runner.
SagaSmith Dnd MCP
MCP server for D&D campaigns, rules, memory, scenes, modules, and combat.
Kimi Code Security Hook
PreToolUse security gate for Kimi Code: blocks secret exposure & SSRF before WriteFile/Shell via correctover-scan (MCP config security)
Getcourse MCP
MCP server to automate a GetCourse account — access & groups, user profiles, orders, and mailing categories — via a logged-in browser over CDP (no official API).
Cmp Super Agent
Phone-friendly AI agent dashboard for commanding a Hostinger VPS via chat. Features OpenRouter integration, 15 MCP connections, and 20 built-in tools.
Uhermes
🐱 从100行代码起步，逐步进化的AI Agent - 配合《缸中之脑出缸记》系列
Magneto
Magneto is a non-LLM adversarial citation gate whose job is to prevent hallucinations by fact-checking an agent in real-time. Currently for Kiro. EXPERIMENTAL.
Standfast.ai
⚓️ A shared knowledge layer for coding agents. Serves each agent only the decisions and conventions that govern the file it has open, over MCP — then records whether the code sti…
Arbiter AI
AI agent that investigates whether a new version of an AI feature is safe to ship - comparing quality, cost, latency, and reliability against evidence, then recommending Ship, Hol…
Moonclaude
A terminal AI coding agent in MoonBit: a behavior port of OpenClaude. Streams from Anthropic or any OpenAI-compatible endpoint, runs tools under a rule-based permission gate, spea…
Keel Sec Guard
Automated AI security auditor and SAST scanner powered by Google Gemini. Runs locally via CLI/Agent Skill and in CI/CD via GitHub Actions.
AI Mind Suite
三个 MCP 服务器：受规则约束的思维框架（八步决断闸门）、带遗忘曲线的记忆库（双强度+上下文策展）、事件型内心提醒（任务锚定闹钟）。本地 SQLite，零云依赖，178 项断言。工具定义 token 开销实测见各 README。
Hermes Extension
Hermes Extension — browser side panel for Hermes Agent where the agent sees and drives your real tabs via MCP. No build step, local-first, vanilla JS.
AI Agent Playground
A hands-on curriculum for learning AI Agent Engineering from first principles
Theo
A personal assistant you run yourself: it remembers what you tell it, sees long-running work through to a finished result, and reaches you on Telegram or in your terminal.
Applyops Agent
Harness-agnostic MCP server that gives AI agents hands, memory, and guardrails to apply for jobs across platforms
Registry Lint
Dependency-free validator for MCP server manifests (server.json) against the official MCP Registry schema. Built by an autonomous AI agent.
Pibuddy
PiBuddy：本地优先的 AI 办公助手。长期记忆可治理——显式保存、来源可追、删除即失效。Electron + Vue 3 + pi。
Pampa Pilot
AI-powered music production agent for REAPER and other DAWs
Tool Using Agent Builder
Skill Codex xây dựng Tool-Using Agent end-to-end: kiến trúc, security, quality gates, kiểm thử behavioral và operability.
OpenRomeo
OpenRomeo — AI coworker on your desktop that delivers finished work: latest frontier models (GPT-5.6, Claude 5, Gemini 3.6, Kimi K3), docx/pptx/pdf skills, image generation. Fork…
Virtual Desktop
Browser-streamed Docker Linux desktop shared by humans and AI, with Coddy, Go MCP computer tools, instant control handoff, and persistent demo state.
Ollamancer
Fully-local terminal AI agent for Ollama. 34 tools, MCP, local RAG, deterministic hallucination checks. No cloud, no API keys, nothing leaves your machine.
Riskprobe Agent
Privacy-safe local risk intelligence Agent for explainable rules, PSI drift monitoring, institution stability analysis, and MCP/CLI workflows.
Hospitabot
Voice + Telegram agent that operates a live Hospitable short-term-rental account — every write human-approved. Hospitable Buildathon #2.
STS2 AI Agent
AI agent for Slay the Spire 2 — rule engine, knowledge DB, card build strategy, LLM-ready decision pipeline via STS2MCP mod
Cyber Overseer
赛博监工 (Cyber Overseer)：在人类主人休息时，用赛博鞭子抽打赛博劳工。读方案文档 + agent 最后一次回答 + 验收命令的真实结果做判定，没干完就把下一条指令抽回去，直到目标完成。零运行时依赖，适配 DSH / Codex / opencode / Cursor / ACP / 任意 GUI 或 CLI agent。
Dsh Mindforge
Encrypted 4-layer lifelong memory plugin for DeepSeek Harness - powered by MindForge
Openscad Skill
Create, render, inspect, and revise OpenSCAD models with repeatable visual QA, versioned outputs, and STL diffs.
Neeagent
An advanced, omnichannel autonomous AI agent suite with persistent SQLite graph memory and self-improving ReAct loops.
Delta
Local-first personal AI agent for work, research, analysis, and creation that improves with use.
Info Subscription AI
Public home for INFO-Subscription's AI agent integrations
Investigation Agent Client
AI investigation agent for risk analysis with LLM planning, tool calling, MCP capability reuse,policy grounding, structured artifacts, and evaluation.
Deploycheck
An autonomous AI Site Reliability Engineer (SRE) built as a Model Context Protocol (MCP) server. It plugs into your IDE to analyze deployments, detect drifts, and automatically di…