by Deodat-Lawson · MCP Server · ★ 894
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is LaunchStack safe to install? View the security audit →
Featured in: Business Diagnosis & Founder Skills
Launchstack The TypeScript engine for AI-native Next.js apps. Ingestion, OCR, RAG, knowledge graph, LLM abstractions, and background jobs — ports-based, framework-agnostic, and designed to be wired into the Next.js app you already have. Quickstart · Packages · Architecture · Reference app · Contributing · Discussions Quickstart ts import { createEngine } from "@launchstack/core"; const engine = createEngine({ db: { url: process.env.DATABASEURL! }, llm: { openai: { apiKey: process.env.OPENAIAPIKEY! } }, embeddings: { indexName: "openai-3-small" }, ocr: { defaultProvider: "DOCLING" }, providers: {}, storage: myStoragePort, // you implement StoragePort (S3, local, etc.) jobs: { dispatcher: inngest }, // or any JobDispatcherPort }); // Use any subsystem const { db } = engine; const results = await engine.rag?
pnpm add @launchstack/core
git clone https://github.com/launchstack/launchstack.gitTaken from the project's README on GitHub. Check the security audit before running it.
No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 894 |
| Forks | 125 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 64.5388116671681/100 |
| Open Issues | 42 |
| Last Updated | 2026-10-14 |
| Created | 2025-01-01 |
| Platforms | claude-code, docker, mcp, node |
| Est. Tokens | ~16k |
These tools work well together with LaunchStack for enhanced workflows:
Looking for a LaunchStack alternative? If you're comparing LaunchStack with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Full-stack AI app generator — FastAPI + Next.js with agents, RAG, streaming, auth, and 20+ integrations out of
Flock is a workflow-based low-code platform for rapidly building chatbots, RAG, and coordinating multi-agent t
This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure whe
Web app for teams of 20+ members. In-built connections to major LLMs via API. Share chats, prompts, and agents
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use
Explore other popular mcp server tools:
LaunchStack is AI-powered StartUp Accelerator Engine built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workfl. It is categorized as a MCP Server with 894 GitHub stars.
LaunchStack is primarily written in TypeScript. It covers topics such as claude, docker, knowlege-graph.
The README on GitHub (github.com/Deodat-Lawson/LaunchStack) gives: pnpm add @launchstack/core , then git clone https://github.com/launchstack/launchstack.git. Usage details are in the same README.
LaunchStack is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to LaunchStack on Agent Skills Hub include full-stack-ai-agent-template, flock, mira-OSS. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: