Archestra Enterprise MCP Gateway
A central place for teams and enterprises to manage MCP and agents at scale.
- MCP Gateway
- LLM Gateway
- Guardrails preventing "The Lethal Trifecta"
- Private MCP Registry
- MCP Orchestrator
- Lightweight & efficient
- Role-Based-Access-Control for multi-team usage
- Metrics exporter
Quickstart
Start with Docker
docker run -p 9000:9000 -p 3000:3000 archestra/platformThe platform is now running with:
- Web UI at http://localhost:3000
- Proxy at http://localhost:9000
Archestra mitigates "The Lethal Trifecta"
The "lethal trifecta" for AI agents is a critical security vulnerability that arises from combining three specific capabilities: access to private data, exposure to untrusted content, and the ability to communicate externally. An attacker can exploit this combination by embedding malicious instructions within untrusted content, such as a webpage or email. Because LLMs follow any instructions they are given, they can be tricked into accessing your private data and sending it to the attacker. This creates a significant security risk, as the LLM cannot distinguish between user commands and malicious instructions embedded in the content it processes.
Examples of hacks:ChatGPT (April 2023), ChatGPT Plugins (May 2023), Google Bard (November 2023), Writer.com (December 2023), Amazon Q (January 2024), Google NotebookLM (April 2024), GitHub Copilot Chat (June 2024), Google AI Studio (August 2024), Microsoft Copilot (August 2024), Slack (August 2024), Mistral Le Chat (October 2024), xAI's Grok (December 2024), Anthropic's Claude iOS app (December 2024), ChatGPT Operator (February 2025), Notion 3.0 (September 2025).
🤝 Contributing
We welcome contributions from the community! Contribution guideline.
Thank you for contributing and continuously making Archestra better, you're awesome 🫶
