- Conduid
- Marketplace
- #agent
MCP servers tagged agent
2.2K live MCP servers tagged "agent", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent.
Faf Agent Public
Public About Repo for FAF Agent. Source private at Wolfe-Jam/faf-agent.
Zest Lang
Token-efficient programming language for LLM tool calls; transpiles to Python; ships with MCP server
Agentk
AgentK is a user-space security kernel for AI agents: an MCP/tool boundary with typed syscalls, taint-aware policy, capability receipts, signed evidence, and replayable flight log…
Myterminal
MyTerminal：连接 ChatGPT 聊天模式与本地开发环境的终端桥梁。支持 Actions/MCP 双通道、多会话协作、Skill 工作流、Subagent 委派，全程可审计。
LLM Agent Harness Survey
模型决定上限，Harness 决定下限：LLM Agent 与 Harness 适配性研究综述 | A Survey on Model–Harness Adaptation (Agent = Model + Harness)
Agent Vm MCP
MCP control plane for dedicated Linux agent VMs with shell, workspaces, persistent coding agents, and pluggable upstream MCP bridges.
Nexus Graph Agent
Self-correcting Agentic RAG system built with LangGraph, hybrid vector search, and Model Context Protocol (MCP) tool servers for multi-hop reasoning and verifiable grounded genera…
Zokai Station Free
A self-hosted, privacy-first AI workstation. Unifies local/cloud LLMs with your documents, email, and calendar in a single Human-in-the-Loop workspace.
Cutible
Agent-native montage engine: Timeline-as-Data, verb API, deterministic FFmpeg render, QC loop, MCP server, ingest pipeline, multi-agent swarm, VLM perception, Remotion, OTIO bridg…
Agentq
agentq
Multidb MCP
A MCP server for database, support muti remote
Claude Office Skills
Import Excel and PowerPoint skills into Claude Code to automate spreadsheets and presentations using local filesystem access.
Uapi Agent Skills
Official UAPI Agent Skills (86 single-endpoint skills for uapis.cn). Install with: npx skills add AxT-Team/uapi-agent-skills
Enso Climate Agent MCP Comparison
Compared several Agent/MCP schemes for modeling ENSO (El Niño and La Niña) climate phenomena.
Claude Md Templates
🚀 Simplify your workflow with CLAUDE.md templates for quick setup, clear project guidelines, and personal preferences without complex configurations.
Web Agent
Local-first web & desktop automation toolkit: browser automation, video transcription, local OCR & VLM vision, desktop control — 数据全部本地处理，零上传
AI Repository Template
This is a template repo for building your AI Marketplace compatible repository.
Agent Fde
带方法论、会积累经验的落地咨询 Agent 工具包：FDE 五阶段流水线 + 分层记忆与技能结晶，作为 MCP server 与 CLI 提供
Codex Harness
Self-hosted WebUI for the open-source Codex agent — approvals, sandbox, terminal, diff, auto-compaction, MCP; works with ChatGPT, Zhipu Coding Plan and custom OpenAI-compatible AP…
Sveda
Open-source embeddable AI agent. JS client, host SDKs, and a self-hosted Rust sidecar.
DevWit
Lean-context AI-native desktop IDE: multi-agent orchestration, authorization gate, transparent context & MCP. 747 unit tests, 3 platforms.
Portzilla
Port and process lease coordinator for parallel AI coding-agent sessions
Agent Authz
Secure-by-default authorization PEP for APIs, Agent tools, RAG, and tasks
Agentoffice
A collaborative Office workspace for people and AI agents. Alternative to Google workspace.
Better Bash
Background process management for LLM coding agents — non-blocking bash with streaming output, stdin, and long-polling
Mdloop
Human-in-the-loop review for agent-written markdown. Self-hostable, Apache-2.0.
Aegisai
Production-oriented AI platform with a centralized Main Agent, Advanced RAG, MCP, agent memory, planning, verification, security, evaluation, observability, and streaming.
Carrystate
v0.2.0: unpack fidelity fixes (sessionless project memories land, MCP name collisions warned, no swallowed write errors), verify/unpack structural validation gate (unsupported spe…
Tygarun CLI
SaaS infrastructure for coding agents — 48 modules, 4,600+ endpoints, zero dependencies
Nova Kernel
The Constitutional AI Operating System. One memory, one skill library, one agent registry, shared across Claude, Codex, Gemini, Cursor and Antigravity. Self-evolving, self-maintai…
Rasputin Mantle
Self-hostable agent platform with live computer view, parallel research, voice, and a Tauri desktop app. CodeAct loop, Docker-sandboxed Chromium, server-enforced cost ceiling, MCP…
Agentic MCP Gateway
A LangGraph-powered gateway for multi-MCP agent workflows with intent routing, observability, and OpenClaw-compatible skill export.
Jev In MCP
MCP relay that adds use_jev to every server: Jev picks the tool calls, the calling model writes the values Jev cannot choose, the relay executes. Built on jev-dev-kit.
Temporal Memory Workflows
Durable Temporal workflow templates with StudioMeyer Memory integration. 5 production patterns: memory-aware agent, operator approval, saga rollback, recurring synthesis, multi-ag…
Reflex Agent
Local-first AI agent + knowledge base for your files. Your second brain on Claude Code or Codex — markdown, scheduled workflows, full recall. No cloud.
AI Agent Deep Dive
Explore AI agent architecture with deep dives, PDF notes, and a minimal Python teaching project for learning core agent structure
Langchain From Zero
🚀 从零到精通 LangChain - 21章完整中文教程 | 使用 vLLM+Qwen、Langfuse、Playwright | Agent/RAG/LangGraph/MCP 全覆盖 | 100+示例
Proc
Rust TUI interactive process manager with network analysis, USB detection, Docker monitoring, security scoring, and terminal recording
Loop Agent
Autonomous software delivery from product brief to verified implementation. Loop plans, builds, tests, and repairs in a task workspace, then hands back reviewable artifacts or Git…
Claude Code Workflows
Build Claude Code workflows, templates, and best practices for faster software development, testing, docs, and code review
AnyCLI
The operating system for AI work. Build, automate, and control real tools with AI.
Agent Skills Vergeos
AI technical-support agent skills for VergeOS — Claude Code plugin and Codex CLI artifacts for diagnostics, the vrg CLI, and training, backed by the public VergeOS Docs MCP.
Mini Harness
A small, interview-ready coding agent harness
Openai Playground Evals Prompt Design
Hands-on experiments with OpenAI Playground covering prompt design, model comparison, tool/function calling, structured outputs, and eval-driven prompt improvement.
Flow Assist
A domain-agnostic terminal assistant: a plugin host with an LLM agent loop, MCP servers over HTTP or stdio, and a chat that asks before it writes
AgenticAI
Agentic AI to train on mcp, vector db, RAG, and memory on json all on local machine
Tc Harness
TC_Harness —— 让小模型稳定调用工具的智能体框架 / Tool-calling agent harness for small language models — connect MCP tools, compress long context, auto-repair malformed JSON/tool history, and retr…
Browser Control Kit
Drive the browser you are already using: real Chrome, real profile, real logins. Tab budget, one approval click, built-in MCP server.
Sshx
Agent-oriented remote host execution over SSH — JSON results, dry-run plans, safety rails, audit trail, MCP server, and an installable Agent skill. Single binary, no remote daemon.
Codex Toolloop
Build agentic coding workflows with OpenAI Codex ToolLoop: Based on the Codex app-server and Vercel AI SDK v6, codex exec automation, JSONL events, structured outputs, dynamic too…