cloud-# ⚡ cloud-ops-mcp

**Production-ready Python Model Context

🇬🇧 English • 🇮🇳 हिन्दी • 🇨🇳 中文 • 🇯🇵 日本語 • 🇪🇸 Español • 🇩🇪 Deutsch • 🇫🇷 Français • 🇰🇷 한국어

CI: Passing • Version: v1.2.0 • Python: 3.10+ • MCP: 2025-03-26 • License: MIT

Quick Start • How It Works • 3-Layer Workflow • MCP Tools • Architecture • Configuration • Security • License

⚡ cloud-ops-mcp

Production-ready Python Model Context Protocol (MCP) server for Cloud Telemetry, Port Diagnostics, Log Analysis & Secret Auditing — built for Claude Desktop, Cursor, Windsurf, Google Antigravity & AI Agents.

💡 How It Works & Token Efficiency

Traditional cloud agent setups dump raw log files and huge infrastructure state dumps directly into the context window, consuming tens of thousands of tokens per request. cloud-ops-mcp implements a claude-mem style 3-layer workflow (Observation -> Index -> Compressed Summary) to inspect and diagnose systems with minimal token overhead.

Related MCP server: devenv-doctor-mcp

⚡ Quick Start & Multi-IDE Integration

1. Claude Code

claude mcp add cloud-ops python3 /path/to/cloud_ops_mcp.py

2. Cursor IDE

Add to .cursor/mcp.json or Global Settings:

{
  "mcpServers": {
    "cloud-ops": {
      "command": "python3",
      "args": ["/path/to/cloud_ops_mcp.py"]
    }
  }
}

3. OpenAI Codex CLI

codex mcp add cloud-ops -- python3 /path/to/cloud_ops_mcp.py

4. Google Antigravity CLI/IDE

antigravity mcp register cloud-ops -- python3 /path/to/cloud_ops_mcp.py

5. OpenCode

opencode mcp install cloud-ops python3 /path/to/cloud_ops_mcp.py

6. Windsurf / Cline

{
  "mcpServers": {
    "cloud-ops": {
      "command": "python3",
      "args": ["/path/to/cloud_ops_mcp.py"]
    }
  }
}

🔄 3-Layer Workflow

Step 1: Snapshot

Capture high-level system state across all cloud clusters and services without loading raw body logs into memory:

snapshot = await call_tool("cloud_ops_snapshot", {"region": "us-east-1"})

Step 2: Filter

Scope and isolate specific anomalies or failing instances based on severity or tags:

filtered = await call_tool("cloud_ops_filter", {
    "snapshot_id": snapshot["id"],
    "severity": "CRITICAL",
    "service": "k8s-ingress"
})

Step 3: Deep Audit

Perform targeted, deep diagnostic verification on isolated resources with zero noise:

audit = await call_tool("cloud_ops_audit", {
    "resource_id": filtered["targets"][0],
    "inspect_secrets": False
})

🛠️ MCP Tools

• cloud_ops_snapshot: Generates instantaneous telemetry index across endpoints.

• cloud_ops_filter: Applies low-token filtering to pinpoint error logs and failed open ports.

• cloud_ops_audit: Conducts exhaustive security checks, network route verification, and secret auditing.

🛡️ Security

See our official SECURITY.md policy for supported versions and vulnerability reporting procedure maintained by NexusVibe AI Tech Security Team.

📄 License

Distributed under the MIT License. See LICENSE for details.mcp Banner" />

MCP Standard: 2025-03-26 • Python 3.10+ • Zero API Keys Required • NexusVibe AI • License: MIT

⚡ cloud-ops-mcp

Production-ready Python Model Context Protocol (MCP) server for Cloud Telemetry, Port Diagnostics, Log Analysis & Secret Auditing — built by NexusVibe AI.

💡 Why This Exists & Token Efficiency

Traditional cloud agent setups dump raw log files and huge infrastructure state dumps directly into the context window, consuming tens of thousands of tokens per request. cloud-ops-mcp implements a claude-mem style 3-layer workflow (Observation -> Index -> Compressed Summary) to inspect and diagnose systems with minimal token overhead.

📊 Token Savings Comparison

🏗️ Architecture Diagram

flowchart TD
    subgraph ClientLayer["AI Coding Assistants & Environments"]
        CC["Claude Code (`claude mcp add`)"]
        CR["Cursor (`.cursor/mcp.json`)"]
        OC["OpenAI Codex CLI (`config.toml`)"]
        GA["Google Antigravity IDE (`mcp_config.json`)"]
        WS["Windsurf / Cline"]
    end

    subgraph MCPEngine["cloud-ops-mcp Engine (NexusVibe AI)"]
        TH["System Telemetry Handler"]
        PD["Port Diagnostics Engine"]
        SA["Secret & Env Auditor"]
        LA["Log Parser & Summarizer"]
    end

    subgraph SystemLayer["Target System / Cloud Environment"]
        OS["Host OS Metrics & Hardware"]
        NET["TCP / Listening Ports"]
        ENV["Environment & .env Files"]
        LOGS["System & Application Logs"]
    end

    CC --> TH
    CR --> PD
    OC --> SA
    GA --> LA
    WS --> TH

    TH --> OS
    PD --> NET
    SA --> ENV
    LA --> LOGS

🚀 1-Click / 1-Command Quick Start

1. Claude Code CLI

claude mcp add cloud-ops-mcp -- python -m cloud_ops_mcp

2. Cursor IDE (.cursor/mcp.json)

{
  "mcpServers": {
    "cloud-ops": {
      "command": "python",
      "args": ["-m", "cloud_ops_mcp"]
    }
  }
}

3. OpenAI Codex CLI (~/.codex/config.toml)

[mcp_servers.cloud_ops]
command = "python"
args = ["-m", "cloud_ops_mcp"]

4. Google Antigravity IDE (mcp_config.json)

{
  "mcpServers": {
    "cloud-ops-mcp": {
      "command": "python",
      "args": ["-m", "cloud_ops_mcp"]
    }
  }
}

5. Windsurf / Cline

{
  "mcpServers": {
    "cloud-ops-mcp": {
      "command": "python",
      "args": ["-m", "cloud_ops_mcp"]
    }
  }
}

🛠️ Included Tools

1. system_health_snapshot — Captures CPU core count, RAM usage, disk space, and OS environment.

2. check_port_status — Checks TCP connectivity and open port listening statuses.

3. audit_env_secrets — Scans environment variables for leaked keys and tokens.

4. analyze_log_file — Extracts error counts, warnings, and stack traces from logs.

🌟 Overview

cloud-ops-mcp is an open-source, light-weight, stdio-based MCP server built in Python. It provides autonomous AI agents with critical real-time cloud operations, system telemetry, security secret auditing, port checking, log analysis, and Docker container inspection capabilities.

🛠️ Tools Included

1. system_health_snapshot

   • Captures real-time CPU core count, disk usage (total, used, free GB), OS platform, and Python environment details.

2. check_port_status

   • Checks TCP connectivity and listening status for target host and ports (e.g., 80, 443, 22, 8080, 5432).

3. audit_env_secrets

   • Scans environment variables or custom .env string inputs for leaked credentials, API tokens (AWS, GitHub, OpenAI), and passwords.

4. analyze_log_file

   • Parses log files or text blobs to extract error counts, warning summaries, and stack trace samples.

5. inspect_docker_containers

   • Queries Docker engine daemon to list running container statuses, images, IDs, and exposed port mappings.

⚙️ MCP Installation & Setup Configs

1. Claude Desktop (claude_desktop_config.json)

Add the following block to your claude_desktop_config.json (located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "cloud-ops-mcp": {
      "command": "python3",
      "args": [
        "/path/to/cloud-ops-mcp/cloud_ops_mcp.py"
      ]
    }
  }
}

2. Cursor (.cursor/mcp.json)

Add the following to your workspace or global .cursor/mcp.json:

{
  "mcpServers": {
    "cloud-ops-mcp": {
      "command": "python3",
      "args": [
        "${workspaceFolder}/cloud_ops_mcp.py"
      ]
    }
  }
}

🚀 Quickstart

Run the server manually over stdio:

python3 cloud_ops_mcp.py

📄 License

MIT License © jitendrakumarvoicex-art (Jitendra_Kumar)

🌐 Universal AI Agent Setup

Integrate cloud-ops-mcp across all major AI development environments and agent frameworks.

1. Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "cloud-ops-mcp": {
      "command": "python",
      "args": ["-m", "cloud_ops_mcp"]
    }
  }
}

2. OpenAI Codex CLI (~/.codex/config.json)

{
  "mcpServers": {
    "cloud-ops-mcp": {
      "command": "uvx",
      "args": ["cloud-ops-mcp"]
    }
  }
}

3. Google Antigravity IDE (.antigravity/mcp_config.json)

{
  "mcp_servers": {
    "cloud-ops-mcp": {
      "command": "python",
      "args": ["-m", "cloud_ops_mcp"]
    }
  }
}

4. Claude Desktop & Claude Code (claude_desktop_config.json)

{
  "mcpServers": {
    "cloud-ops-mcp": {
      "command": "python",
      "args": ["-m", "cloud_ops_mcp"]
    }
  }
}

5. Windsurf / Cline (.windsurf/mcp_config.json / cline_mcp_settings.json)

{
  "mcpServers": {
    "cloud-ops-mcp": {
      "command": "python",
      "args": ["-m", "cloud_ops_mcp"]
    }
  }
}