Skip to main content
An MCP client connecting through two servers — a no-auth documentation server and an OAuth platform server — that opens onto Akua clusters, Kubernetes, installation repositories, and dashboards
Akua is built for agentic operations. You can use hosted agents for guided deployment and operations work, or connect your own coding agent through the Model Context Protocol (MCP). Both paths use the same platform API, workspace controls, and operational context.

What you can do

Agent setup

Configure docs and platform MCP context before changing workspace resources.

Hosted agents

Use the embedded dashboard agent or configure workspace agents that investigate, propose, and automate operations inside Akua.

Documentation MCP

Search and query Akua docs in real-time. No authentication required. Works out of the box with any MCP client.

Platform MCP

Manage clusters, products, and installs via the Akua API from external AI tools. Uses OAuth 2.1 and sandboxed Code Mode.

Installation repositories

How agents read, prepare, and review changes to Akua installations through their git repositories.

Kubernetes access

Give agents direct access to cluster resources through the Kubernetes API proxy and command execution.

Quick setup

Ask your coding agent to fetch the setup prompt:
The prompt handles client-specific setup and tells the agent to start with read-only workspace discovery.
See Agent Setup for server details, manual setup, and the safe first workspace prompt.

Beyond MCP

Akua’s AI integration goes beyond MCP servers:
  • Contextual menu: every doc page offers copy-as-markdown, open-in-AI, and one-click editor setup
  • llms.txt: industry-standard files (llms.txt and llms-full.txt) for AI indexing
  • Agent setup prompt: use Agent Setup for agent-readable setup instructions

Agent setup

Connect docs and platform MCP servers safely.

Hosted agents

The embedded dashboard agent and the full agent product model.

Platform MCP

How Code Mode gives agents full API access in a sandboxed V8 isolate.

Examples

See agents in action: log analysis, security audits, and more.