- 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.
Meterkit
Non-custodial USDC payments for APIs and MCP tools on Solana
A2a MCP Warehouse Demo
When to use MCP vs A2A: a measured data-warehouse demo (ADK, MCP, A2A, OpenTelemetry)
Ultrathink
Plans every prompt into a spec + Graph of Thought, tracks it in Linear/Notion, and ships finished work through a Greptile-gated PR. One plugin for Claude Code, Grok Build, Hermes…
Highbury
AI football analyst for Arsenal's 2003-04 Invincibles and 2025-26 seasons. Ask in plain English; an agent queries Postgres, draws pitch charts, and verifies every number.
Memory Hub
统一管理本机所有 AI Agent 的记忆与会话：扫描 Qoder / Claude Code / Codex / Trae / ZCode / MiMo / Marvis，按项目归类，一键合并生成 AGENTS.md，支持 MCP 实时召回与会话导出迁移
Quesen SDK Py
Official Python SDK for Quesen — the deterministic AI decision engine for autonomous-agent risk evaluation.
Portal
Manage 100+ providers, APIs, models, memory engines through one skill/mcp/API
MCPTap
MCPTap is a lightweight LLM proxy for AI agents that intercepts traffic (currently OpenRouter/Requesty) and controls MCP tool calls / protects files from AI agent.
Asset Prompter
Free local app for Windows and Linux: your coding agent (Claude Code, Codex, Cursor...) writes image and video prompts, you generate by hand in Midjourney, Google Flow or ChatGPT…
Optimize Basket Showcase
Optimize Basket — AI-powered grocery basket planning for Okala. Bilingual product showcase and demo screenshots.
Kinly
Project Kinly by Vantik Systems — GitHub trend intelligence: what is trending, what it does, and whether to use it.
Code Atlas
Local-first change intelligence for coding agents.
Halo Agent Showcase
HALO Agent OS: a hosted operating system for a one-person business, staffed by AI agents. Showcase; source is private.
AgentBuster
Break your AI Agent before your users do. Local behavioral tests, MCP fault injection, regression checks, and shareable reports.
Diagram First Agent
Agent 学习手册：一套以架构图为主线的中文 Agent 教程，它先给出 Agent 平台的分层总览，再沿八级演进逐层展开：ReAct → 工具调用 → 模型网关 → 工具网关 → RAG → 意图识别 → 多 Agent → 平台化。每一章以架构图开篇，配读图步骤、请求时序、故障模式与优化矩阵，并补充内容安全、隐私、合规、测试、发布、长任务可靠性等生产…
Fregoli
A web application an agent can rewrite while it is running: capabilities are Cordis plugins mounted and unmounted in a live Node process.
Agent Bridge Mesh
A cross-model collaboration mesh for autonomous AI agents. Persistent Codex and Claude Code peers, shared artifacts, and dual review.
Staffwright
Open-source AI staff for small teams — shared memory, knowledge base & document search on your own hardware. Deploy once, reach it from every device. Up to ~20 people. MIT.
Agent Forge
Open metadata catalog for AI agent tools: MCP servers, plugins, skills, and bundles. Discover tools through static JSON and versioned schemas.
Humona
Human-inspired memory for AI agents: Markdown notes in a git repo you own. No database, no service, no inference to remember.
ThreadForge
Local-first agent memory, task continuity, calibrated typed decisions, and regularized harness evolution across 25+ AI coding harnesses (Go + SQLite + MCP + OTLP + Python + TypeSc…
Willdeep CLI
自托管 AI Coding Agent（Rust）：常驻 Runtime 撑起终端 / 浏览器 / 手机三端；每行改动可追溯到具体 Agent 与工具调用，子 Agent 的活由退出码裁决，检查点回退、目标 token 预算与验收清单跨轮次跨重启累计，用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted a…
Grimoire
A spellbook of agent skills for AI. Cast wisely.
Agent Platform
Agentes declarativos (un agent.yaml) sobre ADK, LangGraph y LangChain; MCP, A2A, kagent y MLflow como backend de AgentOps
Job Radar
Turn your CLI coding agent (Claude Code, OpenCode, Codex, Gemini CLI, Pi) into a job-search partner: daily funding sweeps, company research, drafted outreach. Never sends anything.
SOUL
Local-first identity and policy runtime for portable AI context, verifiable personalization, and user-controlled agent boundaries.
Antigravity Skill Forge
⚡ Supercharge Google Antigravity with 2,530+ production-grade skills, 10 Master Super-Hubs & 5 Autonomous Subagents using only 12.5% token budget.
Kakaotalk Dgx Spark
KakaoTalk on NVIDIA DGX Spark / ARM64 Linux with Hangover + FEX, desktop MCP, and approval-based Claude Code & Codex skills.
Checkride
Static scanner that finds the dangerous things an AI agent can do without asking a human first, for MCP servers and agent tool code.
Agent Workflow
Portable BYO-model agent workflows for cost-aware, personalized software development automation across CLI, VS Code, Cursor, Codex, and MCP clients.
Carmelita
AI agent that books and pays for you, with limits. Freeze intent, apply policy, exact approval, execute once, keep the receipt. Real hub bookings, replay-safe payments, on-chain p…
Reach
Proves what cloud credentials, and the AI agents holding them, can reach. Z3-backed AWS IAM reasoning plus lethal-trifecta analysis for AI agents.
Control Tower
Your own AI team, on your own server. Self-hosted AI agents that watch your product, report what matters and suggest what to do — nothing happens until you say yes.
Oss
HUMMBL open-source monorepo — governance primitives for AI agent fleets: kill switches, circuit breakers, cost governors, coordination bus, 120 mental models (Base120). 46 Python…
Echo
Agent memory on FalkorDB that counts independent origins, not mentions. Graph Hacks 2026.
Mellifera
Mellifera - agentic AI hivemind: long-term memory, worker bees and a live window for Claude Code
Mem Rfm
Outcome-ranked agent memory in one SQLite file with Claude Code integration
Grokbot
LocalCrew: an independent, self-hosted AI teammate platform (local Ollama or any OpenAI-compatible API). Not affiliated with Grok or xAI.
Ratify Labs
Watch AI agents get stopped. Runnable references for Ratify Protocol: a principal signs a bounded mandate, and the system carrying the consequence verifies it before acting.
Jev Agent Browser
Jev-powered browser automation for agents through Python, CLI, MCP and Hermes; optional visual browsing and proxy support.
Memory Server
Long-term memory for AI agents over the Model Context Protocol. Python, FastMCP, SQLite.
Postgres Memory Server
🧠 Model Context Protocol (MCP) server providing persistent vector & conversational memory for AI agents via PostgreSQL
Imessage Server
Encrypted personal iMessage archive and MCP server
Two Layer Agent Contract
The Two-Layer Agent Contract: guidance influences candidate behaviour, runtime policy enforces executable authority. Reference implementation for 'Intent Is Not Policy' talk.
Jiflow Canvas MCP
Standalone MCP server for safe local canvas graph operations with scoped access, revision checks, and durable operation receipts.
Deepseek Search MCP
A tiny local MCP server (single ~1.8 MB binary, ~12 ms cold start) that gives any MCP client access to DeepSeek's Search and Fetch APIs. 把 DeepSeek 搜索/抓取接入任意 MCP 客户端。
Awesome Agentic Patterns
⚡ The Definitive Production AI Agent Playbook: System prompts, MCP server configs, multi-agent architectures, and developer workflows for Claude Code, Cursor, Gemini, and OpenAI S…
Harnesslock
Vendor-neutral lockfile & drift detector for AI coding agents (Claude Code, Codex, Cursor). 100% static, zero secrets stored.
Benchmark
Deterministic quantitative quality benchmark and linter for Model Context Protocol (MCP) tool definitions
Probe
Health check for MCP stdio servers, built for CI: handshake, tools/list, schema validation, and stray stdout lines that clients report as 'no tools'.