Vibeham Docs

Rock8Cloud exposes an MCP (Model Context Protocol) server that lets AI coding agents interact with your projects, services, environments, and code reviews.

Available Tools

Tool	Description
`list_organizations`	List organizations you belong to
`list_projects`	List projects in an organization
`get_project`	Get project details with services
`list_services`	List services in a project
`list_environments`	List stable and preview environments
`get_code_reviews`	Get code review findings for a branch
`check_github_connection`	Check if a repository is accessible via the GitHub App
`create_project`	Create a new project in an organization
`list_branches`	List branches of a GitHub repository
`create_repo_service`	Create a new repository service in a project
`deploy_service`	Trigger a deployment for a service
`get_deployment_status`	Get the current status of a deployment
`get_latest_build`	Get the latest deployment and build job status for a service environment (`stable` or `preview`)
`get_build_logs`	Retrieve orchestration build logs for a deployment
`get_build_logs_by_build_id`	Same as `get_build_logs` but takes a `buildJobId` directly
`get_runtime_logs`	Retrieve historical runtime logs for any deployment (live or past)

Setup

The MCP server URL for your instance is:

https://app.rock8.cloud/mcp

Authentication is handled via OAuth — each agent will prompt you to authorize on first use.

Claude Code

claude mcp add rock8cloud --transport http https://app.rock8.cloud/mcp

Or add to your project's .mcp.json:

{
  "mcpServers": {
    "rock8cloud": {
      "type": "http",
      "url": "https://app.rock8.cloud/mcp"
    }
  }
}

Zed

Zed does not support remote HTTP MCP servers natively yet. Use mcp-remote as a stdio bridge. Add to your project's .zed/settings.json (or global ~/.config/zed/settings.json):

{
  "context_servers": {
    "rock8cloud": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://app.rock8.cloud/mcp"]
    }
  }
}

OpenCode

Add to your project's opencode.json:

{
  "mcp": {
    "rock8cloud": {
      "type": "remote",
      "url": "https://app.rock8.cloud/mcp"
    }
  }
}

then run opencode mcp auth to authorize

OpenAI Codex CLI

codex mcp add rock8cloud -- npx -y mcp-remote https://app.rock8.cloud/mcp

Or update your ~/.codex/config.toml:

[mcp_servers.rock8cloud]
command = "npx"
args = ["-y", "mcp-remote", "https://app.rock8.cloud/mcp"]

IntelliJ

Open Settings → Tools → AI Assistant → Model Context Protocol, click Add, choose STDIO, and paste:

{
  "mcpServers": {
    "rock8cloud": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://app.rock8.cloud/mcp"]
    }
  }
}

Troubleshooting

If your MCP client uses mcp-remote as a bridge (like Zed or Codex CLI), you might occasionally encounter the following error when calling tools:

JWKSNoMatchingKey: no applicable key found in the JSON Web Key Set

This happens when the OAuth key set rotates and the cached token states fall out of sync. To fix this, entirely remove your local cached credentials directory:

rm -rf ~/.mcp-auth

This ensures mcp-remote will prompt you for a clean, brand new OAuth access token flow on the next tool execution.

First Deploy Workflow

The MCP server includes a first_deploy prompt template that guides AI agents through deploying a repository for the first time. The flow:

Validate locally — agent checks for a Dockerfile (creates one if missing), reads the EXPOSE port, ensures changes are committed and pushed
Check GitHub connection — check_github_connection verifies the GitHub App can access the repository
Create project — create_project creates a new project to group your services
Select branch — list_branches lets you pick which branch to deploy
Create service — create_repo_service registers the service with its Dockerfile and port configuration
Deploy — deploy_service triggers the build and deployment, returns the URL where your app will be live

To start a first deploy, ask your AI agent to "deploy this repository" or use the first_deploy prompt if your agent supports MCP prompts.

Code Review Workflow

The get_code_reviews tool is designed for agents running inside a repository. A typical workflow:

Agent detects the current branch (git branch --show-current)
Agent calls list_organizations to find your org ID
Agent calls get_code_reviews with the org ID and branch name
Agent receives findings with severity, file locations, and fix suggestions
Agent discusses findings and can apply fixes using the fixPrompt field

This lets you interactively resolve code review feedback without leaving your editor.

Verify Connection

After setup, verify the MCP server is connected:

Claude Code:

claude mcp list

Other agents: Check the MCP or tools panel in your IDE settings — rock8cloud should appear with the tools listed above.

MCP Integration