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-0.1.3.tar.gz (13.4 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-0.1.3-py3-none-any.whl (15.6 kB view details)

Uploaded Python 3

File details

Details for the file xenfra_mcp_server-0.1.3.tar.gz.

File metadata

  • Download URL: xenfra_mcp_server-0.1.3.tar.gz
  • Upload date:
  • Size: 13.4 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-0.1.3.tar.gz
Algorithm Hash digest
SHA256 5df6aa7a42d9dbda4d75852d299e9c9ca927418ca82dd6bf00a24319ae9e057f
MD5 61f495541d1931179fb78ace4268496a
BLAKE2b-256 ead9ee2fad81e22c0d3271a18b9529ad87efc3d0b27ef7eb74f7875097b4c490

See more details on using hashes here.

File details

Details for the file xenfra_mcp_server-0.1.3-py3-none-any.whl.

File metadata

  • Download URL: xenfra_mcp_server-0.1.3-py3-none-any.whl
  • Upload date:
  • Size: 15.6 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-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 ced80618e9ab3e0a595240d253d51eaf925d59cdf90eb582788a0c45116ecf2e
MD5 84e9034666195deaa98aca2b91ce7688
BLAKE2b-256 37b300bc57572ad2e97903365b4e2cc20ba8f29d5f837b4c5a2e05e451dfa69a

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