Archestra

v1.0.0Coding Agentsstable

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

a2aa2a-mcpacpagentai
Share:
3,724
Stars
0
Downloads
0
Weekly
0/5

What is Archestra?

Archestra is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enterprise ai platform with guardrails, mcp registry, gateway & orchestrator

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enterprise AI Platform with guardrails, MCP registry, gatewa

Use Cases

Enterprise AI platform with guardrails and MCP registry
Multi-agent orchestration and gateway
archestra-ai

Maintainer

LicenseAGPL-3.0
Languagetypescript
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx archestra

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Archestra

Archestra is an enterprise AI platform that provides a private MCP registry, ChatGPT-like chat interface, Kubernetes-based MCP server orchestrator, built-in RAG knowledge base, and security guardrails including prompt injection protection and tool-level data exfiltration prevention. It runs entirely on-premises via Docker, giving teams a governed, cost-monitored environment for deploying and sharing MCP servers across the organization. Engineers and AI teams use it to centralize MCP server access with enterprise-grade security, observability, and up to 96% cost reduction through dynamic optimization.

Prerequisites

  • Docker with Docker socket access (/var/run/docker.sock) on the host machine
  • Ports 9000 (API/backend) and 3000 (UI) available on localhost
  • Kubernetes access if using the full MCP server orchestration features
  • An MCP client such as Claude Desktop or any MCP-compatible tool
1

Pull and run the Archestra platform container

Run Archestra in quickstart mode. The Docker socket mount enables the platform to orchestrate MCP servers as containers. Two named volumes persist the PostgreSQL database and application data.

docker pull archestra/platform:latest
docker run -p 127.0.0.1:9000:9000 -p 127.0.0.1:3000:3000 \
  -e ARCHESTRA_QUICKSTART=true \
  -v /var/run/docker.sock:/var/run/docker.sock \
  -v archestra-postgres-data:/var/lib/postgresql/data \
  -v archestra-app-data:/app/data \
  archestra/platform
2

Access the Archestra UI

Open http://localhost:3000 in your browser. Complete the initial setup wizard to configure your organization, create admin credentials, and set up your first team.

3

Register MCP servers in the private registry

From the Archestra UI, navigate to the MCP Registry section and add your self-hosted or remote MCP servers. Archestra manages API keys, OAuth credentials, and server lifecycle, so individual developers never need direct access to secrets.

4

Configure AI model connections

Add your LLM provider API keys (Claude, GPT-4, Gemini, DeepSeek) in the platform settings. Archestra routes requests through its cost optimizer and tracks usage per team.

5

Connect your MCP client to Archestra

Configure your MCP client to use Archestra as the MCP server endpoint. The platform exposes a unified MCP endpoint that proxies to all registered servers.

{
  "mcpServers": {
    "archestra": {
      "command": "npx",
      "args": ["mcp-remote", "http://localhost:9000/mcp"]
    }
  }
}

Archestra Examples

Client configuration

MCP client configuration pointing to a locally running Archestra platform backend.

{
  "mcpServers": {
    "archestra": {
      "command": "npx",
      "args": ["mcp-remote", "http://localhost:9000/mcp"]
    }
  }
}

Prompts to try

Example prompts once Archestra is running with MCP servers registered.

- "List all MCP servers registered in our organization's registry"
- "Search the knowledge base for our internal API documentation on the payments service"
- "Show me token usage and cost breakdown for the engineering team this week"
- "Deploy a new instance of the GitHub MCP server for the frontend team"
- "Check the security guardrail logs for any blocked tool calls in the last 24 hours"

Troubleshooting Archestra

Container fails to start with Docker socket permission error

Ensure the user running Docker has permission to access /var/run/docker.sock. On Linux, add your user to the docker group: 'sudo usermod -aG docker $USER' and re-login.

Ports 3000 or 9000 are already in use

Check what is using the ports with 'lsof -i :3000' or 'lsof -i :9000'. Stop conflicting services, or modify the docker run command to map to different host ports (e.g., -p 127.0.0.1:3001:3000).

Data does not persist after container restart

Ensure you are using named volumes (-v archestra-postgres-data:/var/lib/postgresql/data and -v archestra-app-data:/app/data) rather than anonymous volumes. Named volumes persist across container restarts. Verify with 'docker volume ls'.

Frequently Asked Questions about Archestra

What is Archestra?

Archestra is a Model Context Protocol (MCP) server that enterprise ai platform with guardrails, mcp registry, gateway & orchestrator It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Archestra?

Follow the installation instructions on the Archestra GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Archestra?

Archestra works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Archestra free to use?

Yes, Archestra is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "archestra": { "command": "npx", "args": ["-y", "archestra"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Archestra?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides