Candor UI

Guides / v0

Candor UI with v0

Connect the docs MCP server from the prompt's + menu, give v0 the brief, and ask for a chat built from the registry.

  1. 01Add the registry

    v0 builds Next.js apps with shadcn/ui, so the registry works as it does anywhere else: ask v0 to add @candor to components.json and install from it with npx shadcn@latest add @candor/<name>. Or paste the registry entry yourself when you have the code open.

    JSON · components.json
    {
  "registries": {
    "@candor": "https://candor.themethodic.com/r/{name}.json"
  }
}

    See:Get started

  2. 02Add the docs MCP server

    The docs MCP server at https://candor.themethodic.com/mcp is 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. v0 takes a custom MCP server: open the + menu in the prompt form, choose MCPs, then configure a custom server with this address. Pick No Auth; the server needs none. There's no config file to edit, so there's no snippet here. v0's docs don't name the transports it speaks; the server answers streamable HTTP.

    The server's address

    See:v0: MCP integrations

  3. 03Give it the brief

    There's no skills directory to install into, so put the brief where the tool reads instructions: in the prompt itself, or wherever your v0 project keeps its instructions. The llms.txt index lists every docs page as Markdown; llms-full.txt has every component with its props.

    Text · Brief
    Use Candor UI (shadcn/ui components for AI agents): https://candor.themethodic.com/llms.txt
Registry: add "@candor": "https://candor.themethodic.com/r/{name}.json" under "registries" in components.json, then npx shadcn@latest add @candor/<name>.
Start with thread, message and composer; tool-call for tool calls.
Rules: model output is text, never HTML or links; unknown values stay unknown; a control that can't be used says why.

    See:llms.txtllms-full.txt

  4. 04Try 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

    See:ThreadComposerTool callPatterns