Back to Home
archestra-ai icon

archestra

Verified Safe

by archestra-ai

Overview

A centralized AI platform for managing, securing, and optimizing Model Context Protocol (MCP) servers and AI agents, offering features like chat interfaces, private registries, Kubernetes orchestration, dynamic tools for security, cost monitoring, and observability.

Installation

Run Command
docker run -p 9000:9000 -p 3000:3000 -v archestra-postgres-data:/var/lib/postgresql/data -v archestra-app-data:/app/data archestra/platform

Environment Variables

  • ARCHESTRA_DATABASE_URL
  • ARCHESTRA_API_BASE_URL
  • ARCHESTRA_FRONTEND_URL
  • ARCHESTRA_AUTH_ADMIN_EMAIL
  • ARCHESTRA_AUTH_ADMIN_PASSWORD

Security Notes

The platform demonstrates a very strong focus on security, including non-root execution, minimal Alpine Linux base, and robust authentication/authorization via 'better-auth'. It integrates secrets management with HashiCorp Vault, AWS Secrets Manager, and Kubernetes secrets. Critically, it implements advanced AI-specific security measures such as 'Dual LLM' sub-agents to mitigate prompt injections and 'Autonomy Policies' for fine-grained control over tool invocation arguments and trust levels of tool results. While E2E tests include default admin credentials, these are explicitly for testing and environment variables are used for production overrides.

Similar Servers

Stats

Interest Score96
Security Score9
Cost ClassHigh
Avg Tokens2000
Stars306
Forks71
Last Update2025-12-06

Tags

Centralized AIAI PlatformSecurityObservabilityCost ManagementKubernetesDockerMCPAgent Orchestration