Skip to main content

Xenfra Model Context Protocol (MCP) Server - Deploy to DigitalOcean with AI-powered diagnosis.

Project description

Xenfra MCP Server (The Bridge) 🧠

PyPI License: MIT

A Model Context Protocol (MCP) server that empowers AI agents (Claude Desktop, Cursor, Windsurf) to securely deploy, monitor, and debug infrastructure on Xenfra.

Philosophy: Tools as Skills. We expose atomic, reliable infrastructure capabilities that LLMs can orchestrate.

🤖 Available Tools

Tool Description
xenfra_deploy Deploys the project in the current working directory.
xenfra_get_logs Fetches filtered, colorized logs for a deployment.
xenfra_get_status Retrieves real-time health metrics (CPU, RAM, Uptime).
xenfra_security_scan Scans codebase for 15+ types of secrets before deployment.
xenfra_list_projects Lists all active deployments and their IDs.
xenfra_context Dumps environment summary for "Why is it broken?" queries.

📦 Installation & Configuration

For Claude Desktop

  1. Make sure you have uv installed.

  2. Edit your config file:

    • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  3. Add Xenfra:

{
  "mcpServers": {
    "xenfra": {
      "command": "uvx",
      "args": ["xenfra-mcp-server"]
    }
  }
}
  1. Restart Claude Desktop. Look for the 🔌 icon.

For Custom Agents

You can run the server directly via stdio:

uvx xenfra-mcp-server

🛠️ Usage Example

User: "Deploy this app and check if it's healthy."

Agent (Using Xenfra MCP):

  1. Calls xenfra_security_scan -> "No secrets found."
  2. Calls xenfra_deploy -> "Deployment started, ID: dep_123."
  3. Calls xenfra_get_status -> "Status: 🟢 Running."

🔗 The Xenfra Ecosystem

This MCP Server is the "Brain Connector" of the Xenfra Open Core architecture:

  • xenfra-sdk: The Core Engine (Used by this Server).
  • xenfra-cli: The Terminal Interface.
  • xenfra-platform: The Private SaaS Backend.

🤝 Contributing

We welcome contributions! Please see CONTRIBUTING.md for details.

📄 License

MIT © Xenfra Cloud

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

xenfra_mcp_server-0.1.1.tar.gz (13.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

xenfra_mcp_server-0.1.1-py3-none-any.whl (15.3 kB view details)

Uploaded Python 3

File details

Details for the file xenfra_mcp_server-0.1.1.tar.gz.

File metadata

  • Download URL: xenfra_mcp_server-0.1.1.tar.gz
  • Upload date:
  • Size: 13.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.26 {"installer":{"name":"uv","version":"0.9.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for xenfra_mcp_server-0.1.1.tar.gz
Algorithm Hash digest
SHA256 db8f2c3ab824e29737bbc85fa87737f33bfb14d4e7afd378d9b6ada9815d3f1c
MD5 e783a2f3c2322fc4853172d7f085dc12
BLAKE2b-256 dc8fc205fe5567ea34d322362bcb008d462c76e580450f3005099335b067559f

See more details on using hashes here.

File details

Details for the file xenfra_mcp_server-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: xenfra_mcp_server-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 15.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.26 {"installer":{"name":"uv","version":"0.9.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for xenfra_mcp_server-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 70142ccb857b9054a3286822c76eb9867dd1c566f90ebb9af33f3134f2f05d54
MD5 cfd17ac6873797937dea7c91a5a5a4e4
BLAKE2b-256 fba9443098c0ccd96e2bced47ec46207f6402f4590727af437b3b451d3b06380

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page