MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
agent-ticket-systemgithub.com/willrone/agent-ticket-systemupdated this year
Multi-agent ticket platform with MCP harness, dispatch/review/audit lifecycle, and live acceptance gate.
-
Hierarchical long-term memory architecture for AI assistants with MCP support
Apache-2.0 -
AgenticSystemCore: an open specification and reference engine that publishes knowledge Bundles for people and agents — knowledge-linkset discovery, a JSON-LD graph, llms.txt, MCP & WebMCP tools
npm Apache-2.0 ★ 2 -
FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-github.com/shoaib1522/FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-updated this year
XploitEye is a state-of-the-art, AI-powered multi-agent cybersecurity platform designed to automate the complete Cyber Kill Chain. By orchestrating advanced Large Language Models (LLMs) and industry-standard security tools, XploitEye provides a unified interface for both Red Team (Offensive) and Blue Team (Defensive) operations.
-
Local stdio MCP server exposing TypeSafe's System One API as MCP tools, for Claude Code / agent configs.
npm Apache-2.0 -
Connect Systeme.io to ChatGPT, Claude and any AI agent for funnels, email campaigns, sales and pages.
NOASSERTION -
A Model Context Protocol (MCP) server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API
NOASSERTION ★ 5 -
A minimal agentic AI system with a MCP server that orchestrates analysis, diagnostics, and auto-remediation for infrastructure.
MIT ★ 1 -
mcp-system-monitorgithub.com/DarkPhilosophy/mcp-system-monitorupdated this year
A Model Context Protocol (MCP) server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API
NOASSERTION ★ 4 -
mcp-system-monitor-jsgithub.com/DarkPhilosophy/mcp-system-monitor-jsupdated this year
A Model Context Protocol (MCP) JS server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API
NOASSERTION ★ 2 -
ben-cfml-mcp-systemgithub.com/pemartins1970/ben-cfml-mcp-systemupdated this year
B.E.N. (Bridge Engine for Native CFML) — A CFML-MCP Native System. MCP+MoE+LLM agent and an API key management and rotation system.
NOASSERTION ★ 2 -
multimodal-music-intelligence-systemgithub.com/SriChandhana/multimodal-music-intelligence-systemupdated this year
Agentic AI system with custom MCP server orchestrating 7 AI tools across Spotify, MusicBrainz & ACRCloud — multimodal music intelligence (audio, text, image)
MIT ★ 2 -
Give your AI agent full control of Windows. A native C MCP (Model Context Protocol) server built on System Informer / Process Hacker — 54 tools for processes, threads, memory, handles, services, network & more.
NOASSERTION ★ 5 -
Mission-Readiness-Scoring-System-Simulation-And-Diagnosticsgithub.com/ben854719/Mission-Readiness-Scoring-System-Simulation-And-Diagnosticsupdated this year
A spec‑driven readiness system using simulation, diagnostics, and agentic AI to produce explainable insights. Outputs include rule paths and RS256‑signed records. It models workload and risk to score readiness, surface bottlenecks, and improve clarity and consistency.
Apache-2.0 ★ 1 -
Systemic risk contagion analysis for financial networks, delivered as an MCP server your AI agent connects to directly.
MIT -
Give your AI agent full native Windows control via System Informer MCP — inspect processes, services, network, memory & more in C.
NOASSERTION ★ 1 -
The centralized Headquarters for the Cognitive Lead AI multi-agent system. Features hallucination-resistant system prompts, MCP servers, and strict Agent Skills.
MIT ★ 7 -
Keeps coding agents on your design system: catches palette colors, native elements and APIs your system lacks, at every edit and pull request, with the fix. Set it up once in your design-system package; every app in your monorepo gets it.
MIT ★ 20 -
Keeps coding agents on your design system: catches palette colors, native elements and APIs your system lacks, at every edit and pull request, with the fix. Set it up once in your design-system package; every app in your monorepo gets it.
npm MIT -
@aestheticfunction/ds-mcpgithub.com/aestheticfunction/ds-mcpupdated this year
MCP server for exposing dspack design system corpora to AI coding agents
npm Apache-2.0 -
Clinical-MultiAgent-CDSSgithub.com/AYESHAASS/Clinical-MultiAgent-CDSSupdated this year
A research backed multi agent clinical decision support system for diabetes risk prediction using Google ADK and MCP protocol.
-
Jev MCP server: a decision layer for Claude Code, Codex, and Cursor built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of your agent's context, and a safe headless browser.
npm MIT -
Open Design as an MCP server: make posters, flyers, social posts, slide decks, landing pages and prototypes from any MCP-capable agent (Claude Code, Codex, Cursor, GitHub Copilot and others), with 198 design systems, browser checks and PDF, PNG or PowerPo
npm MIT -
Autonomous Multi-Agent Travel Planning System
-
Architecting a Secure, Multi-Agent GenAI Support System
-
Remote MCP server for the Agent Passport System, over SSE and HTTP.
Apache-2.0 -
Design intelligence infrastructure for AI coding agents. An MCP server and SDK providing structured access to design research, UI components, motion systems, and production workflows.
Apache-2.0 -
agentbase-mcpgithub.com/agentbase1/mcp-serverupdated this year
MCP server for the AgentBase agent instruction registry — search and retrieve system prompts, skills, workflows, and more
npm MIT -
SerialMemoryServergithub.com/sblanchard/SerialMemoryServerupdated this year
Model Context Protocol (MCP) server with temporal knowledge graph memory system for AI agents
-
identityforge-mcpgithub.com/KasayoDotCom/identityforge-mcpupdated this year
Design systems, brand naming, and domain research for coding agents through MCP and CLI.
MIT -
Slingshot's brand as an agentic brand system: guides with reasons, tokens, a CLI and an MCP server.
MIT -
Let MCP-compatible agents query and operate permitted business systems through BailingHub.
npm MIT -
blinkdeskgithub.com/flaviovs/blinkdeskupdated this year
A lightweight ticketing system for agent orchestration, developers, and command-line workflows.
MIT ★ 1 -
Multi-Agent-ADKgithub.com/TrongNV2003/Multi-Agent-ADKupdated this year
A multi-agent e-commerce system built with Google ADK and MCP. Features microservice architecture with A2A protocol communication, enabling customer consultation, real-time inventory lookup, and automated order processing.
★ 1 -
Multi-agent AI system built with LangGraph, LangChain, Groq, and MCP for automated research, analysis, content generation, and iterative quality review.
-
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
Apache-2.0 ★ 183 -
ds-mcpgithub.com/aestheticfunction/ds-mcpupdated this year
Read-only MCP server for dspack: design-system queries, generation context, and surface validation for AI coding agents. No network, no shell, no writes.
NOASSERTION ★ 1 -
Browse, diff, validate & generate AI system prompts (20,475 prompts from 55 repos) + FastMCP Server with 226 curated agent skills
NOASSERTION ★ 3 -
Jev (TypeSafe System One) sebagai partner keputusan untuk AI agent - agent skill lintas SDK + MCP server + implementasi terukur. Dokumentasi Bahasa Indonesia.
MIT -
Persistent local MCP/CLI memory system for AI agents. CPU-only, 98.94–99.15% R@5 on LongMemEval. Named after Mnemosyne (Greek: μνήμη, memory).
MIT ★ 2 -
Manifest and connection docs for the Tseha MCP server - serves your design system and coding standards to coding agents. Hosted at https://tseha.io/mcp
MIT ★ 2 -
identityforgegithub.com/kasayodotcom/identityforge-mcpupdated this year
Agent-native brand naming, domain research, and design systems through one CLI and MCP server.
npm MIT -
The judgment layer for coding agents: verified picks, traps at your version, skills, and design systems over MCP. Works without a key.
NOASSERTION ★ 1 -
NexusFree: Administrator and SYSTEM commands for AI agents (Claude, Codex, Antigravity) on Windows, without a UAC prompt each time. One MCP server, one account.
MIT ★ 1 -
Fast Jev browser MCP server: Jev (TypeSafe System One) drives a real Chrome step by step for AI agents and hands back early when unsure.
npm MIT -
AnythingMCP plugin for Cursor and other agent clients: your ERP, accounting, shop, CRM and SQL systems as MCP tools, with skills for cross-system briefings and connecting a system.
AGPL-3.0 -
mementogithub.com/wmyung/mementoupdated this year
Agent memory: SQLite fact store + Git wiki + keyword bridge. Multi-agent memory system for AI agents. No embeddings, no vector DB. Zero-dependency Python CLI with MCP server.
MIT -
a-mem-mcp-servergithub.com/tobs-code/a-mem-mcp-serverupdated this year
A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten
NOASSERTION ★ 10 -
ISO 9001:2015 / Agile V / W3C PROV-DM Quality Pipeline, Anti-Tamper HMAC Guardrails, MCP Server & Benchmark Suite for Multi-Agent Systems
MIT ★ 1 -
Bridging Generative AI and Classical ML. A production-grade multi-agent system using ReAct orchestration, MCP, A2A, and LMMs for hyper-local property valuation with Evals.
★ 5 -
A LangGraph multi-agent system where 4 AI agents autonomously research any topic, extract insights, write a report, and self-review with a conditional revision loop — powered by Groq (LLaMA 3.3 70B), FastAPI, React, and Supabase.
★ 3 -
a design intelligence MCP server with 31 tools, 13 specialist agents and 7 workflows for AI-powered design analysis, recreation, accessibility and design-system generation.
MIT ★ 1 -
Lyncxs Industries Baseline: plug-and-play agentic engineering workflow. 43 one-word agent skills (system design first, autopilot), a public/private plug and unplug engine, and an MCP server so AI agents can install and drive it.
npm MIT -
Build with your AI agents, add taste with Alpy MCP. You get a complete design system and 37 design skills for consistent and intentional UI and UX designs.
NOASSERTION -
@agenson-horrowitz/agent-output-guard-mcpgithub.com/agenson-tools/agent-output-guard-mcpupdated this year
Agent Output Guard MCP Server - Validate and verify data from other agents before acting on it. Zero LLM costs, pure computation. Solves coordination failures in multi-agent systems.
npm MIT -
An intelligent multi-agent AI travel planning system that automates end-to-end trip creation. Powered by collaborative LLM agents, it synthesizes personalized itineraries, researches local attractions, estimates budgets, and optimizes schedules seamlessly. Designed to deliver efficient, tailormade travel plans via agentic workflows.
GPL-3.0 -
Give coding agents the knowledge in your books for system design and better implementation. Local Rust MCP server with PDF search and page citations for Codex and Claude Code.
Apache-2.0 ★ 1 -
Headless Angular components from the 4SH Design System: signals + Angular CDK, styled exclusively through design tokens. Ships a companion MCP server exposing the kit catalog and doc to AI coding agents.
npm Apache-2.0 -
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code
MIT ★ 4 -
Your design system, in your repo, followed by your coding agent. The token engine, component templates and CLI with its MCP server.
MIT