MCP servers tagged mcp
61K live MCP servers tagged "mcp", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with mcp.
TGS 2025054471 Autonomous AI Agents
WSQ Autonomous AI Agents (TGS-2025054471): 2-day visual courseware with 18 hands-on Hermes Agent and OpenClaw labs.
AI Universal Memory
Portable, zero-dependency project memory for any AI coding engine or human — handoff, decisions, facts and state that survive across sessions and engines.
Delegate To Deepseek Harness
Codex Agent Skill: delegate bounded coding work to DeepSeek Harness, then independently review and verify. Methodology-first, backend-agnostic.
AgentToolGate
本地 AI Agent 工具治理网关：不防提示词注入发生，防注入得逞后的高危工具调用后果（policy / approval / audit / MCP 双向治理）
MetatraderMCP
MCP server for MetaTrader MQL4/MQL5 documentation (4853 entries). Provides AI assistants with complete MQL reference for Expert Advisor development.
CRA Knowledge Base
EU Cyber Resilience Act knowledge base as an OKF bundle for Meerkat and MCP
DevHotel
Every project gets its own room — a browser for isolated local development servers. Easy Setup · Easy Change · Easy Check · Easy Undo
Layntra
Open-source Codex plugin and local Figma companion for controlled inspect, plan, apply, and undo workflows.
Asana Sweep
Scheduled AI sweep of your Asana tasks - triage, dedupe, and open GitLab issues that trigger an AI coding harness.
R Code
Session-first AI coding desktop app built with Rust, Tauri 2, React and TypeScript.
Assemora
Build visually. Extend with TypeScript. Control with AI. — a TypeScript framework and CMS where one application layer serves developers, people and AI agents.
Tracebench
RCAgentBench: a benchmark measuring how tool design and agent instructions affect LLM agents doing root cause analysis on distributed traces.
Dsh Plugin Coaligne
CoAligne for DeepSeek Harness: shared team project context over MCP, plus the coaligne-workflow skill
Corpus Ingest Core
Deterministic, provenance-tracked pipeline that turns spoken content into verified, searchable knowledge. MCP server + Claude Skills.
Liberde
☁️ Hosted/cloud build (Postgres + Vercel) of Liberde — an open-source, self-hostable Claude.ai for every model via OpenRouter: artifacts, design studio, web search, MCP + custom t…
Roelint
Turn Rules of Engagement into a policy firewall for red-team commands and AI agents
GDMU Academic Runtime
基于 MCP 协议构建的高校 Academic Copilot 框架，将 AI Agent 与教务系统连接。目前支持广东医科大学正方 V9.0，实现智能选课规划、成绩分析、学分审核以及自动化教务工作流。
Claude Multi Agent Investing
Claude Code framework: 12 AI agents (Buffett/Munger/Burry personas + analysts) debate your portfolio through 13 commands. Tax-aware for Canadian accounts. Advisory only.
Workflow To Skill
Turn goals and existing Agent tools into readable, reviewable, reusable workflow Skills.
Vocal
On-device text-to-speech for macOS — right-click any text to speak it. Rust host + Swift MLX engines (Qwen3-TTS / Chatterbox) + Tauri + MCP. 100% local, multilingual.
Awesome Agent Reliability
The curated map of the agent-reliability field.
KI Stack
KI-Stack is a modular, transaction-safe framework for deploying and managing a fully local AI environment on Windows. It provides preflight checks, self-tests, logging, rollback,…
Skillkeeper Test Repo
A fixture repository for SkillKeeper.
Builder 2
Generic governed local platform for agent-assisted software development. Goose + deepagents + MCP, governed by explicit authority boundaries, HITL gates, and durable artifacts. Ze…
ClaudeSwitch
A lightweight profile manager and switcher for Claude Desktop.
Computer Use Plus
Low-token, low-latency Windows computer-use MCP with learned shortcuts, UIA/CDP/OCR routing, and DeepSeek Harness support
Skillvet
Scan AI agent skills & MCP servers for phone-home, secret access, and postinstall before you run them. npx skillvet ./my-skill → RED/YELLOW/GREEN
Gym Tracker
🏋️ The tool you needed for your AI coach
Velvet Rope
Test whether blocking one AI-agent route actually prevents the real-world effect. ShadowPath maps and replays alternate authorization paths.
Browserlink
Freehand annotation + element inspection for Chromium and Comet. MV3 extension, local REST hub, MCP server, Hermes adapter.
Stackchan Milo
Recipe and source for a StackChan K151 desk face under Hermes Agent.
Froggy Bottom Line
Turn a Screaming Frog crawl into role-specific, prioritised action plans that people without SEO knowledge can actually execute.
AppTelepath IOS
AI-agent-first remote debugging SDK for iOS — logs, network capture, UI tree, screenshots, crashes and simulation, over MCP.
Ego Agent Infra
Evidence-gated multi-agent ResearchOps infrastructure for embodied AI
AI Knowledge Base Indexer
通用知识库索引器 · Universal Knowledge Base Indexer — 一键将散乱 Markdown/HTML 笔记分类生成总索引，支持项目来源标记，零依赖，AI Agent 友好
Pydantic AI Tech Intel Briefing
Pydantic AI assistant for public-source technology intelligence and daily Chinese briefings.
Hardware Logging
Structured, crash-aware serial logging for embedded boards — built for AI coding agents. Persistent sessions, decoded backtraces, bounded queries, MCP server.
Cineops Agent
Gemini-powered media pipeline incident investigation agent for Agentic Cinema
Dsh Statecore
Native memory plugin for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore
Sdd Harness
A spec-driven development harness for coding agents: instruction layering, a documentation model, risk-matched review, and the gates that keep them honest.
Parfait
On-device meeting notetaker for macOS — an open-source Granola alternative. Records, transcribes, and summarizes meetings locally with Apple Intelligence, with your own Claude acc…
Sre Investigation Agent
Incident-investigation chat agent on Amazon Bedrock AgentCore Runtime, with a live-streaming UI and its own MCP server for per-prompt cost/token/tool-call metrics
Glm4v Vision MCP
GLM-4.6V 图像理解 MCP：识图/OCR/图表解析，原生接入 DeepSeek Harness（dsh-mcp-client），也兼容 Codex/Cline 等
Commonmind
Universal memory for human and agent teamwork — transactional, distributed, built on CockroachDB and AWS serverless.
Graflet
Precomputed knowledge graphs of versioned library docs, for AI agents. Docs as a graph, not snippets.
Cloudguard
Reliability and safety harness for LLM cloud agents. Tool-selection accuracy vs. tool count, blast-radius guardrails, and prompt-injection red-teaming against a real AWS mock. Eve…
Dsh Plus
MCP catalog and Vision Bridge for DeepSeek Harness — manage MCP in Settings, caption chat images for text-only models.
Dsh Stitch Designer
DeepSeek Harness (DSH) 插件 · Google Stitch AI 设计预览 · 文字生成 UI / APP / Web / 桌面软件界面 · 会话内实时预览 · 对话迭代 · 1:1 HTML 导出（DeepSeek / DSH plugin / AI design / UI generation / MCP）
Daemonaudit
Red/blue security audit for self-hosted AI agent daemons — finds the secrets, the open doors, and the blast radius.
AgentWrite
Multi-Agent AI Writing Workbench — Config-driven agent assembly with Google ADK, streaming output, personalized memory (Vector + BM25 + Reranker), and async task execution. Java 1…