MCP Server

Preview — The CloudThinker MCP server is in early access. The tool surface and transport options may change before general availability. Contact us to join the preview.

CloudThinker can act as a Model Context Protocol (MCP) server — MCP is an open standard that lets AI apps use external tools — so an MCP-compatible AI client can call CloudThinker tools and read CloudThinker data using your workspace’s authenticated context. This is the inverse of the existing MCP connection, which lets CloudThinker agents call your external MCP servers.

What it enables

Capability	Description
Cloud operations in your IDE	Query your cloud inventory and costs from Cursor, Claude Desktop, or any MCP-compatible client
Use your connections	Reach the databases, Kubernetes clusters, and observability tools you already connected to CloudThinker
Run skills remotely	Invoke your workspace skills from an MCP-compatible host
Shared context	Read the same recommendations, dashboards, and incident history the web console shows

Get access

The MCP server is not yet generally available, so the exact tool list, transport options, and authentication setup are shared with preview participants rather than published here. Contact us to join the preview and receive the current client configuration for your workspace. To use external MCP servers as agent tools today, set up an MCP connection — that direction is generally available.

MCP Connection

Connect external MCP servers as CloudThinker tools

API

Same operations over a REST surface

Skills

Package domain knowledge into reusable workflows

CLI

Terminal access to the same capabilities

APIs & Tooling

Deployment

What it enables

Get access

MCP Connection

API

Skills

CLI

​What it enables

​Get access

​Related

MCP Connection

API

Skills

CLI

What it enables

Get access

Related