backend · ai
Filter in Explore Model Context Protocol
10 production projects and 1 rule set built with Model Context Protocol.
Production projects
- Shell History Sync Classic Atuin Atuin keeps history local in SQLite and encrypts it before sync, so the Axum sync server stays a thin store; a gRPC daemon and capability crates (CLI, server, AI, dotfiles) let each part evolve behind feature flags.
- Multi-Agent Interactive AI Classroom Classic OpenMAIC Built as a Next.js app around a set of npm-published packages (slide DSL, generation, renderer, editor, importer, storage). The multi-agent LangGraph pipeline, the slide format and persistence can each be reused or swapped, and heavy video rendering runs in a separate container.
- Local AI Voice Cloning & Speech Studio Hybrid VoiceStudio Heavy model work stays in a Python FastAPI backend with a pluggable, hardware-aware engine registry. Desktop, web, MCP and remote-worker clients all use the same local API, so voice models run on the user's own GPU without a cloud dependency.
- LLM Knowledge Base & RAG Platform Classic WeKnora Retrieval, agents and the API sit in one Go service, and parsing is delegated to a Python gRPC service. Storage backends are pluggable, so the same codebase runs as a lite SQLite binary or a full Kubernetes deployment on existing Postgres, Elasticsearch or vector databases.
- Hybrid Deterministic + LLM Agent Code Review Tool Hybrid Open Code Review A single static Go binary keeps the review engine fast and easy to distribute through npm, CI and IDE plugins. Putting deterministic diff/context analysis before a narrow LLM loop keeps reviews precise and cheap in tokens compared with general-purpose agents.
- Open-Source SEO Research Platform Hybrid OpenSEO Running on Cloudflare Workers with D1, Workflows and Durable Objects makes it free-tier friendly to self-host and to scale when hosted. Supporting both D1 and Postgres through Drizzle, plus a Docker path, keeps the project portable beyond Cloudflare.
- Multi-Model AI Agent & Chat Workspace Hybrid LibreChat A Node/Express API with a Mongoose-modeled MongoDB store handles chat state, while Vite builds the React client separately; optional Docker sidecars for pgvector, Meilisearch, and a Go OpenTelemetry relay keep RAG, search, and observability decoupled from the core API.
- Local-First Sync Engine Classic ElectricSQL Postgres logical replication and shape-based HTTP sync live in a dedicated Elixir OTP service so any TypeScript, React, or Elixir client can subscribe to partial replicas without each client re-implementing replication.
- AI Copilot & Assistant SDK AI-agent CopilotKit A shared AG-UI protocol plus a PlatformAdapter-based channel architecture let one agent implementation power web, mobile and chat-platform surfaces from a single Nx/pnpm monorepo instead of building a separate integration per surface.
- LLM Observability AI-agent Langfuse Storage is split by workload: Postgres via Prisma for relational app state, ClickHouse for high-volume trace analytics, and Redis-backed BullMQ for async jobs, while a separate Rust Axum service handles latency-sensitive LLM proxying outside the Node runtime.
Often used with Model Context Protocol
AGENTS.md rules and agent skills with Model Context Protocol
Questions about Model Context Protocol
How many production projects use Model Context Protocol?
10 verified production projects in the STACK IT FAST directory use Model Context Protocol, each with a full architecture breakdown.
What is Model Context Protocol most often used with?
Across projects in the directory, Model Context Protocol is most commonly paired with TypeScript, React, PostgreSQL.
Is there an AGENTS.md rule or Claude Code skill for Model Context Protocol?
Yes — Jev Browser Agent (Playwright + TypeSafe System One) includes a full AGENTS.md, CLAUDE.md, Cursor .mdc rule set and an installable SKILL.md covering Model Context Protocol.