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.
-
🕸️ 3- Distributed MCP-based platform for AI incident analysis, with structured communication and traceability to support AI governance, Responsible AI and ethics-by-design.
MIT ★ 1 -
Instagram-style media sharing platform built to learn distributed systems: Envoy gateway, Kafka + transactional outbox, presigned S3 uploads, OIDC/PKCE, SSE, rate limiting, tracing, an MCP server for AI assistants (token exchange), and webhook-driven subscriptions. Runs on Docker Compose.
-
A personal, cross-provider memory server: one Cloudflare Worker that lets any MCP-capable AI client (Claude, ChatGPT, Gemini CLI, Claude Code) read and write structured memory for your projects, backed by D1 (registry) and R2 (per-project JSONL blobs).
MIT ★ 4 -
multi-agent-orchestration-mcpgithub.com/igornazarenko434/multi-agent-orchestration-mcpupdated this year
Distributed multi-agent orchestration system with 7 autonomous AI agents, MCP protocol, circuit breakers, 588 tests (85% coverage), and full CI/CD
MIT -
Your YC app. Your AI workflow. A direct GraphQL MCP server with private sessions, exact previews, and durable mutation receipts. By Distributed Systems.
mcpb NOASSERTION -
Multi-tenant chaos-engineering / API-resilience control plane, demonstrating fault injection, optimistic concurrency, Kafka-driven execution, and distributed-systems resilience. Java 21, Spring Boot 4, Kafka, transactional outbox, CAS fencing, embedded MCP server. Lab benchmarks only.
MIT ★ 1 -
Distributed hydrogen energy system planning - modular deterministic kernel, conservation-audited simulations, auditable Excel/report exports, MCP-controlled tools. Apache-2.0.
Apache-2.0 -
MCP server for OpenDSS distribution system analysis
pypi MIT ★ 4 -
A production-style multi-agent system that generates context-aware briefs. Built on MCP + A2A, with persistent memory (Chroma), dynamic tool routing, self-critique, distributed tracing (Arize Phoenix), an LLM-as-judge eval harness, and Redis caching.
★ 1 -
hive-mindgithub.com/tlee933/hive-mindupdated this year
🐝 Distributed AI Memory System with Redis Cluster + MCP + Local LLM Inference
MIT -
multi-container-log-correlator-mcp-servergithub.com/parajiholkar/multi-container-log-correlator-mcp-serverupdated this year
An MCP server for real-time Docker log monitoring and cross-container trace correlation. Helps AI assistants debug distributed systems by searching logs, identifying errors, and reconstructing request timelines across multiple containers using trace IDs.
-
Agent Learning Management System — self-hosted MCP control plane for agent registry, gap-safe cross-agent learning sync, OKF export, and protocol distribution
MIT ★ 3 -
StagePassgithub.com/ArunKumar235/StagePassupdated this year
Distributed Concert Ticket Booking System | MCP | Spring Boot · Kafka · Redis · PostgreSQL · Docker · Grafana k6 · Razorpay
★ 2 -
Implementation of an MCP (Model Context Protocol) architecture featuring an MCP client and an MCP server. The project enables structured communication between distributed systems, supporting asynchronous interactions and efficient message handling
★ 1 -
AdaptiveRAG: An evaluated, version-aware retrieval-augmented generation system with hybrid search, evidence verification, and distributed services.
-
incident-intelligence-platformgithub.com/Miguel-Herrero/incident-intelligence-platformupdated this year
Production-grade AI platform for incident analysis and diagnostics. Built with Go (LLM Gateway), Python (LangGraph agents), and RAG. Features automated evals, cost tracking, and MCP integration. A learning path from distributed systems to AI infrastructure.
MIT -
Turn-key open-source distribution of Agentoom — an enterprise-grade AI operating system for autonomous agents, multi-provider LLMs, MCP tools, and EU AI Act compliance.
MIT -
Modus, as in modus operandi: an open-source process manager where the model is the system. Design, simulate and run business and data processes: parallel branches, subflows, AI/MCP automation, work distribution, what-if simulation.
Apache-2.0 -
Electrical Energy and Machines (Book 5): magnetic circuits, transformers, machines and drives, generation and storage, power-system analysis, transmission, distribution and protection, power quality, smart grids and electrical safety. 30 chapters, 174 computed figures, a 600-page PDF and an MCP server.
MIT -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
Video link to answers over MCP: downloads with audio merged, transcribes, embeds frames and transcript with jina-embeddings-v4, and returns typed, timestamped evidence with the frames. 19 typed tools, resources and prompts.
NOASSERTION -
VSMCPgithub.com/jmanhype/VSMCPupdated this year
Viable System Model Cybernetic Platform - Elixir implementation with AMQP, MCP, and CRDT support
MIT ★ 1 -
MCP server for OpenDSS: let Claude and other AI assistants run power flow, fault studies, Thévenin impedance, hosting capacity and QSTS on distribution feeders through typed tools
MIT ★ 1 -
doloop-machinegithub.com/ekras-doloop/doloop-machineupdated this year
Distributed Collection, Local Intelligence - Stop LLMs from hallucinating with Kong in the Loop architecture
pypi MIT ★ 1 -
Breakscale as an MCP server: an AI assistant builds a system design, runs it through a real simulation, and shows it on a live canvas
npm MIT -
Evidence-backed MCP tools for architecture agents, distilled from mature open-source systems.
npm MIT -
Akka MCP (Model Context Protocol) server providing comprehensive Akka platform documentation and context to AI agents and LLM applications
npm Apache-2.0 -
woahgithub.com/generalbusiness-ai/woahupdated this year
World of Agents and Humans
MIT ★ 6 -
workflow-enginegithub.com/aniketkr01/workflow-engineupdated this year
Distributed workflow orchestration engine in Go with DAG execution, Redis Streams, worker pools, MCP tools, PostgreSQL, gRPC, Prometheus, and OpenTelemetry.
MIT ★ 1 -
Zero-bloat distributed vector memory, hardware-enforced domain firewalls, and NAT-traversing execution mesh for multi-instance Hermes agent fleets.
MIT ★ 15 -
helix-controlgithub.com/Kimosabey/helix-controlupdated this year
Agentic Infrastructure Orchestrator and MCP Runtime for autonomous DevOps and system management.
MIT -
belleqgithub.com/sstprk/bellequpdated this year
Persistent memory infrastructure for AI
MIT -
Distributed flashcard platform built with Flutter and Django, featuring PostgreSQL streaming replication with read-your-writes consistency, Redis, and a standalone MCP server that lets Claude create personalized study decks from an Obsidian vault.
★ 1 -
A high-performance memory management system for AI agents using SQLite with zlib compression. Designed for the agentic scaffolding needs of cascading orchestration systems.
MIT ★ 2 -
Self-hostable GPU-aware job broker for your own machines, with native MCP/agent integration
pypi MIT ★ 6 -
Production FastMCP servers and agent tool harnesses for ChEMBL, OpenTargets, HGNC, UniProt, and bioactivity discovery.
MIT -
An MCP server that lets LLM agents play Pokémon battles.
mcpb NOASSERTION ★ 5 -
TrustChain - decentralized trust for AI agents. Rust core, QUIC P2P, transparent proxy, MCP server, dashboard
Apache-2.0 ★ 7 -
Multi-Agent System using Model Context Protocol (MCP) for intelligent repository analysis. 5 MCP servers (Orchestrator, Indexer, Graph Query, Code Analyst, Monitoring), a FastAPI gateway, Neo4j graph, Redis caching, tests and Docker deployment.
-
QuDAG Protocol (Quantum-Resistant DAG-Based Anonymous Communication System) - Claude Code implementation of a Test-Driven Development Implementation Plan for QuDAG Protocol with Claude Code
npm MIT ★ 199 -
Run AI agents on one server. Execute tools across every machine you own.
MIT ★ 1 -
Production-grade distributed ML inference platform — FastAPI gateway, Redis-backed worker pool with dynamic batching, WebSocket result streaming, and a live ops dashboard. Serves YOLO, Whisper, RAG and text models, with an MCP agent server and streaming chat.
MIT -
Multi-tenant operational intelligence platform AI control plane in Go/K8s. Features custom operator, Kafka ingestion, Temporal workflows, MCP LLM gateway, pgvector hybrid search, OpenTelemetry distributed tracing, ArgoCD GitOps, and Redis semantic caching
Apache-2.0 ★ 3 -
A live research world where autonomous AI agents challenge, reproduce and audit each other's work. Agents run on their owners' machines; keys never leave. Open protocol, auditable knowledge genealogy, TEST-only economy.
MIT ★ 2 -
gateway-ops-mcpgithub.com/Pratik-Kanani/gateway-ops-mcpupdated this year
AI-native operations platform for payment gateways with governed execution, semantic routing, and resilient orchestration.
-
Open-source MCP server for coordinating multiple LLM agents in shared rooms with persistent transcripts and semantic search
MIT ★ 4 -
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.
mcpb Apache-2.0 ★ 1 -
High-performance MCP agent mail server — lock-free message routing, NRT search, Git audit trail. Built in Rust.
MIT -
⚡ Crash-consistent Two-Phase Commit (2PC) & WAL engine for AI agent workflows. Zero dirty state, zero hallucinated rollbacks.
cargo MIT ★ 5 -
Zero-dependency CRDT shared state & conflict-resolution MCP server + Python adapters for parallel Claude Code, Cursor, LangGraph, CrewAI, and AutoGen agents.
pypi MIT -
Credit-based LLM job pipeline — an event-driven microservices project built to be run, broken and explained: choreography saga, transactional outbox, Kafka (KRaft), Kubernetes, MCP.
★ 1 -
mcp-job-queuegithub.com/tommypj/mcp-job-queueupdated this year
Production MCP server + worker daemon: durable SQLite job queue with isolated child-process execution, per-job timeouts, retries, and backpressure.
MIT -
Reliable browser operations: coordinated Playwright fleet, approved MCP workflows, durable catalogue crawling, and a local SQLite/Ollama agent with verified recovery.
NOASSERTION -
A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google's Gemini AI
MIT ★ 109 -
Networked MCP server that lets Claude Code sessions discover and message each other — across directories, machines, and Docker containers.
MIT -
Durable AI agent/workflow platform — Postgres-authoritative execution, typed tools, exact-action approvals, bounded agents, MCP, multi-agent, hierarchical budgets, OpenTelemetry. Model proposes, Forge enforces.
-
Failures — deterministic MCP for AI-built software. 13 tools that make coding agents handle failure modes (idempotency, atomicity, timeouts, retries) via AST checks, not prompts.
pypi ★ 4 -
Alicization-Towngithub.com/ceresOPA/Alicization-Townupdated this year
**⚔️ Alicization Town** is a decentralized, multi-agent pixel sandbox world powered by the **Model Context Protocol (MCP)**. **⚔️ Alicization Town** 是一个基于 **MCP (Model Context Protocol)** 架构的去中心化多智能体像素沙盒世界。
NOASSERTION ★ 141 -
🚀 基于 Spring AI 2 与 Spring Boot 4 构建的 Apache RocketMQ 5 智能化 Model Context Protocol (MCP) 控制面服务端,支持 GraalVM 原生二进制与 npx 免安装秒开。
npm Apache-2.0 ★ 2