Guides / JetBrains IDEs
Candor UI with JetBrains IDEs
Add the docs MCP server in AI Assistant's MCP settings, install the skill for Junie, and build a chat.
01Add the registry
In a React 19 app with Tailwind 4 (Next.js or Vite),
initadds the@candorregistry tocomponents.json, installs the theme and imports it after Tailwind;--yesanswers shadcn's questions, so a coding agent can run it. Without the CLI, add the registry tocomponents.jsonby hand and install withnpx shadcn@latest add @candor/<name>.Set up CandorAdd the chat coreJSON · components.json { "registries": { "@candor": "https://candor.themethodic.com/r/{name}.json" } }See:Get started
02Add the docs MCP server
The docs MCP server at
https://candor.themethodic.com/mcpis remote (streamable HTTP), read-only and needs no key: it searches these docs, reads any page and suggests components for a task. It serves docs, never paid source. In Settings | Tools | AI Assistant | Model Context Protocol (MCP), click Add, choose the HTTP connection type, paste this JSON, pick global or this project, then OK and Apply; the Status column shows the connection. The key isurl; AI Assistant's docs give no separate transport key for this form.JSON · In the New MCP Server dialog, as JSON { "mcpServers": { "candor": { "url": "https://candor.themethodic.com/mcp" } } }03Install the skill
The skills CLI knows Junie, JetBrains' coding agent, and installs the skill into
.junie/skills/in your project. AI Assistant has no skills directory the CLI knows; give it llms.txt as context instead, or paste the skill's text into your project's rules.Install the skill for Junie04Try it
With the server and the skill in place, the agent can look up Thread, Message, Composer and Tool call in these docs and install them with the CLI. Check what it installed against
candor-lock.json.An example prompt