Skip to main content
Skip table of contents

Cloudaware MCP - Overview

This page provides an overview of Cloudaware MCP server, covering its purpose, core capabilities, and supported use cases.

About

Cloudaware MCP (Metadata & Query Proxy) Server provides a secure AI data layer on top of your Cloudaware CMDB and Google BigQuery Export Project. It enables LLM-based tools (ChatGPT, Claude, GitHub Copilot, and others) to:

  • Understand the Cloudaware CMDB as a structured data model

  • Explore object types, fields, and relationships

  • Execute SQL queries against your BigQuery export

This allows AI assistants to navigate your infrastructure data, answer questions about resources and dependencies, and generate code and reports based on real Cloudaware data.

Key Capabilities

CMDB as a Self-Describing Graph

MCP exposes the Cloudaware CMDB as a self-describing graph of objects, fields, and relationships. Any compatible LLM can:

  • Discover object types and their API names

  • Inspect fields, labels, and data types

  • Understand how objects are related (relationship graph)

  • Reason about infrastructure without navigating the UI

Under the hood, tools such as search_types, search_fields, get_relationship_graph, analyze_field, and execute_query enable AI agents to follow a “discover first, query later” pattern.

Direct SQL Access to BigQuery Export

MCP provides AI with controlled SQL execution against your Cloudaware BigQuery Export Project:

  • Explore datasets and tables

  • Join infrastructure and cost/usage data

  • Build custom reports and dashboards

  • Power engineering and analytics workflows

Queries are executed using the execute_query tool against your existing Export Project and SObjects dataset.

Bring Your Own LLM

MCP is model-agnostic and integrates with:

  • ChatGPT

  • Claude Code and Claude.ai

  • GitHub Copilot

  • Gemini CLI

  • LM Studio and local models

  • Internal chatbots and AI assistants

  • Other MCP-enabled tools

Your teams retain their existing toolchains (IDEs, CLIs, and internal assistants), while MCP makes Cloudaware data available within those tools.

Enterprise-Grade Security

MCP is designed as a read-only execution layer operating under the authenticated identity.

  • AI can read metadata and execute queries only within that identity’s permissions. MCP does not introduce additional privileges

  • Access is scoped to the selected Export Project and SObjects dataset

  • MCP inherits the same permissions as the authenticated user (HTTP via Google OAuth 2.0) or the configured service account (local execution)

  • All access respects existing BigQuery IAM permissions

If a user does not have access to a dataset in BigQuery, MCP will not expose it to AI tools.

Use Cases

AI Resource Finder

MCP enables AI-driven resource discovery without manual UI searches. Engineers, FinOps analysts, and architects can ask an AI assistant to:

  • “Find all EBS volumes matching this pattern.”

  • “List S3 buckets in these accounts with their key properties.”

  • “Show all resources that match these filters.”

AI Navigator for CMDB

MCP makes CMDB self-explanatory for onboarding, troubleshooting, and in-product AI assistance scenarios:

  • “Explain what a specific object or field represents”

  • “Show where a given CI is stored”

  • “Find objects related to a service, account, VPC, or environment”

This is the backend capability for any AI helper embedded into the Cloudaware UI.

Inventory Research and Data Exploration

With MCP, an LLM can explore the CMDB structure, explain objects and values, and guide engineers through the data – without requiring them to first build complex list views or reports. Examples:

  • “Analyze my inventory and show what exists for this application”

  • “Compare these sets of resources under the given conditions”

  • “Suggest where to look for this CI or attribute”

Developer Automation Accelerator

Before MCP, developers typically needed to:

  • Study CMDB SObjects and their relationships

  • Build ETL jobs or many API calls

  • Manually discover which fields to use in scripts

With MCP, an AI assistant can:

  • Generate Python scripts that interact with Cloudaware APIs or BigQuery

  • Select the correct objects and fields based on metadata

  • Compose queries and joins that follow the actual relationship graph

This reduces the time to build automation from weeks or months of discovery to minutes of interaction with an AI tool.

Auto-documentation and CMDB Intelligence

MCP enables AI-driven documentation of your data model:

  • Document structures of CMDB objects

  • Describe field purpose and semantics

  • Build dependency graphs between services and resources

This is especially valuable for complex, long-running environments and for onboarding new team members.

! Next step – check Cloudaware MCP - Configuration for setup instructions, supported HTTP transport modes, and system requirements

JavaScript errors detected

Please note, these errors can depend on your browser setup.

If this problem persists, please contact our support.