archestra
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
- 4.4k estrellas
- 1.2k forks
- 102 issues abiertos
- Lenguaje: TypeScript
- Licencia: NOASSERTION
- actualizado
Instalación
git clone https://github.com/archestra-ai/archestra{
"mcpServers": {
"archestra": {
"command": "node",
"args": ["/path/to/archestra/dist/index.js"]
}
}
}{
"mcpServers": {
"archestra": {
"command": "node",
"args": ["/path/to/archestra/dist/index.js"]
}
}
}- Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
- Replace any <placeholder> values with your API keys or paths.
- Restart Claude. The MCP server and its tools appear automatically.
Clone https://github.com/archestra-ai/archestra and follow its README for install instructions.
Nota editorial
Archestra is a self-hosted, MCP-native enterprise platform that centralizes MCP server management away from individual developer machines into a shared, governed orchestrator. Deployable via a single Docker command or on Kubernetes, it provides a private MCP registry for distributing self-hosted and third-party MCP servers org-wide, a ChatGPT-style chat interface with a company-wide prompt registry, and a built-in retrieval-augmented generation knowledge base that requires no external vector database. It connects to Claude (including Claude Code migrations via an included migration kit), as well as OpenAI, Gemini, and DeepSeek models through its MCP gateway layer. A standout security feature is its dual-LLM architecture, which isolates potentially malicious tool responses in a separate sub-agent to block prompt injection attacks and prevent data exfiltration through MCP tools. Platform teams gain credential governance, cost controls, and AI usage observability, while developers can deploy MCP servers organization-wide without handling security infrastructure themselves.
Resumen de MCP Servers
Lo que la gente pregunta sobre archestra
¿Qué es archestra-ai/archestra?
archestra-ai/archestra es mcp servers para el ecosistema de Claude AI. Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator Tiene 4.4k estrellas en GitHub y su última actualización registrada es del 2026-10-23.
¿Cómo se instala archestra?
Puedes instalar archestra clonando el repositorio (https://github.com/archestra-ai/archestra) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar archestra-ai/archestra?
Nuestro agente de seguridad ha analizado archestra-ai/archestra y le ha asignado un Trust Score de 87/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene archestra-ai/archestra?
archestra-ai/archestra es mantenido por archestra-ai. La última actividad registrada en GitHub es del 2026-10-23, con 102 issues abiertos.
¿Hay alternativas a archestra?
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.