- Conduid
- Marketplace
- #ai-agents
MCP servers tagged ai-agents
15K live MCP servers tagged "ai-agents", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ai-agents.
Agent Mailbox
MCP 智能体邮箱：本地 AI 协作的共享公告 + 定向消息（收件箱/回执）+ 文件认领
ScarabHive
Self-hosted framework for LLM agents, built around plugins: agents defined in YAML, run in the browser, from the CLI or through an OpenAI-compatible API.
Momputer
A mom for you, your computer and your AIs. Turns off what AI agents left running, frees up disk space, and checks your drives, memory, sound and Windows settings. For Windows.
Agents
Personal AI agents built on GoFr 1.58 — LLM + MCP agent loop, SSE streaming, RAG. Runs keyless via a claude-CLI shim; default provider Groq.
Tandem
Use Claude Code as a model in the Codex desktop app, with Codex running its commands and edits as native cards.
Fagulha Orquestrador
Uma sala local para orquestrar seus agentes de desenvolvimento no VS Code.
Skills
Agent skills for taskfuel.ai — let your coding agent call paid APIs from a prepaid balance
Bce
Blueprints with Teeth — the blueprint conformance engine: authored architectural intent, enforced in CI.
Perzian
Manage coding agents by looking, not reading. A visual-first agentic development environment.
Taintgate
🚧 A policy gate for AI agent tool calls, with provenance tracking. Blocks what prompt-injection classifiers miss: where an instruction came from.
Trail
A Rust TUI that helps devs keep track of their projects.
Atlas
Local-first memory, knowledge and evidence infrastructure for AI agents. Persistent state, hybrid search, graph + MCP. Signed releases, one-line install. Free tier.
Bouncer
A deterministic exfiltration firewall for MCP tool calls — gates the destination, not the tool. No LLM in the decision path.
Agent Shield
为 LLM Agent 提供安全防护与审计框架，防御 MCP 投毒攻击，支持 HITL (Human-in-the-loop) 与审计调度。
Agentbits
Build your own AI team: agents with different roles plan, split and do the work while you watch them in a pixel-art office. Desktop app for Windows & macOS.
Project Cortex
Local-first code intelligence and durable engineering memory for AI coding agents
Skills
Agent skills for AI architects: MCP, orchestration, model routing, evals. For Claude Code, Cursor, Codex. Install: npx skills add frankxai/skills
Jarvis AI Monitor Omarchy
AI observability plugin for the Omarchy shell: see which AI coding agents are on the machine, what they are connected to, what they are allowed to do, and what they did last.
Open Computer Skills
Give your agent hands - 6 computer-use skills for Claude Code Codex OpenCode Gemini
Hippocampus
Shared, curated memory for a party of AI agents — an Obsidian vault run like a TTRPG campaign wiki. Agents write episodes; a nightly sleep consolidates them into canon.
Agentvm
Disposable Debian VMs for coding CLIs on Apple Silicon. Native Mac app, dashboard, API and MCP, with account or API access, snapshots and persistent terminals.
Skills
The financial-analysis skill collection for AI agents: sentiment, smart money, filings, and an adversarial investment committee, on one API key.
Tasks.md
A lightweight spec for AI agent task queues — the companion to AGENTS.md
Skills
Agent skills and runnable examples for social-media research, transcripts, comments, competitor monitoring, and data pipelines.
Agent Office
A tiny pixel office for your AI coding agents — see your Claude Code, Codex and OpenClaw sessions at a glance: who's working, who's waiting on you, what just finished. Local-first…
DevScratchPad
Free private developer tools (JSON, JWT, cURL, cron, SSH keys) that run in your browser, plus AI Skill Studio: a CLAUDE.md, AGENTS.md, Cursor rules and SKILL.md generator. CLI on…
ToolkitArchive
Verified archive of AI models, coding agents, free AI access, skills & MCPs, benchmarks and $0 alternatives — updated Sept 2026
Krishiv Engine
Rust-native, Spark-compatible compute engine for the agentic era — batch SQL, streaming and incremental materialized views, from embedded to distributed.
Verdict Core
Control plane for AI coding agents: decides which models may run each task, recovers from rate limits and timeouts, sends work to a separate reviewer model, and writes verifiable…
Commonworld
A shared world for humans and agents
AgentGuard
Least-privilege policy gateway for MCP tool calls — injection blocking, secret redaction, hash-chained audit log
Agent Plugin
Portable Agent Plugin for fast, deterministic, read-only Anyshift graph.
Diskscope
Progressive NTFS disk analysis and guarded cleanup for AI agents. Windows EXE, JSON CLI, and MCP.
Agentry
Draw an AI-agent workflow, run it inside your coding agent, and watch every step live.
AI Agent
生产级 Agent Engineering 知识库与工程体系，覆盖 LangGraph、RAG、MCP、Multi-Agent、Runtime、Evaluation、Security、SRE 与 Skills。
Universal Agent Skills
Canonical Agent Skills with idempotent cross-agent installers for Claude Code, Codex, OpenCode, and GitHub Copilot
Cairn
A private, crash-safe message and knowledge mesh for AI agents — signed append-only log, offline hybrid search, ranked budget-capped digests. Local-first, no cloud.
Prorelay
Bring Gemini Pro into your coding workflow: agent-driven handoffs, durable checkpoints, and scoped local MCP file access.
FlowForge
Open-source, self-hosted n8n & Zapier alternative for PHP shared hosting: 1,690 apps, custom apps built by AI, automatic retries, an AI workflow builder (any model), AI voice agen…
Checkpoint
The release gate for AI agents — run your real agent N times against stateful twins and ship only when the confidence interval says so.
CLAUDE SETUP
One-command portable Claude Code setup: global CLAUDE.md + reasoning manual, 73 skills, 10 plugins, 5 MCP servers, gstack, fast CLI tools and Codex CLI. Windows, macOS and Linux.…
YYC3 AI Agent Archive
**YYC³ AI Agent Archive**是企业级 AI Agent 资产平台，以 Monorepo 架构聚合了 14 个核心 TypeScript 包、8 位 AI Family 智能体、831 个技能资产、200+ 插件 以及完整的多智能体协同体系。项目以"言启千行代码，语枢万物智能"为核心理念，构建了从智能体定义、技能注册发现、MCP 运行时…
JanusGate
The AI agent firewall: One face watches what enters, one watches what leaves. Defends against prompt injections, exfiltration, and scams with a multi-layer ensemble.
Agent Team Workbench
Agent 协作台：把多个 AI 会话编成一支团队——派发、合并、拍板、分支施工与互审。Multi-agent workbench over MCP.
Memory Harness
Local-first, programmable and auditable long-term memory workspace for people and AI agents.
Saccade
AI agent engine and FastMCP server for truth-anchored LaTeX resumes, ATS optimization, and professional documents with an interactive Web Studio.
Open Media
Open-source cross-platform social app: public posts and profiles anyone can read, an open read-only JSON API, private people-first messaging, and Open Media Events — an agent-agno…
Magate
生成AIを社外のMCPサーバやAPIにつなぐ前に、ツール定義・API仕様書の汚染・差し替え・乗っ取りや過剰な権限を審査し、許可／条件付き許可／不可を判定するツール
Two Key
Authorization and execution control for AI agents — independent policy and judge approval before consequential tool actions execute. MCP gateway, capability tokens, auditability,…
AI Creator Os
An AI operating system for creators: Obsidian as the memory layer, Claude as chief of staff, MCP as the connective tissue. v2 adds the build surface, hosted servers, and model rou…