cubic
dev.cubicv1.0.0Updated Oct 1, 2026
Triage cubic AI code review findings, start PR reviews, and read wikis, scans, and team learnings.
Overview
AI-generated overview
Lets an assistant triage cubic AI code review findings, start pull request reviews, and read wikis, scans, and team learnings.
- What it does
- This remote MCP server connects an assistant to cubic, an AI code review service. According to the registry description, it supports triaging cubic AI code review findings, starting PR reviews, and reading wikis, scans, and team learnings. No individual tools are listed in the manifest, so the exact operations are not documented here.
- When to use it
- Worth considering when a team already uses cubic for AI code review and wants an assistant to help work through review findings, kick off PR reviews, or pull in related wikis, scans, and team learnings during development. It is not useful for teams that do not use cubic.
- Requirements
- A remote streamable HTTP endpoint at no local package or runtime is declared. The manifest declares no authentication, environment variables, or headers, but access to a cubic account or workspace is likely needed in practice.
Before you install
The manifest declares no authentication, environment variables, or headers, so how the connection is authorized is unclear; confirm this before connecting. Reviewing code and starting PR reviews can expose private repository content to a third-party service, and starting reviews may trigger actions in the team's cubic workspace.
Installation
In SourceWeft
- Open cubic in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"cubic": {
"type": "http",
"url": "https://www.cubic.dev/api/mcp"
}
}
}Tools
0Tool metadata has not been indexed yet.
Version history
1- v1.0.0LatestOct 1, 2026


