Connect shadcn/ui to Codex
Give Codex governed access to shadcn/ui’s 7 tools through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add shadcn/ui to Codex in four steps
Admins approve the server once. Everyone in Codex then gets it through the same governed connection.
- 1
Approve shadcn/ui in Runlayer
Add shadcn/ui from the catalog and choose who can use it and which of its tools are allowed.
- 2
Connect Codex to Runlayer
Install the Runlayer CLI so Codex can reach shadcn/ui, which runs on the user’s machine. Auto Sync can then write shadcn/ui into Codex on macOS, Windows, and Linux.
Codex setup guide - 3
Sign in to shadcn/ui
Sign in the way shadcn/ui requires. Runlayer holds the credentials so they stay out of the client’s configuration.
- 4
Use shadcn/ui from Codex
shadcn/ui’s approved tools appear in Codex. Every call is checked against policy and recorded.
Tools
7 shadcn/ui tools in Codex
Runlayer policy decides which of these Codex users can call.
Get project registries
Get configured registry names from components.json - Returns error if no components.json exists (use init_project to create one)
List items in registries
List items from registries (requires components.json - use init_project if missing)
Search items in registries
Search for components in registries using fuzzy matching (requires components.json).
View items in registries
View detailed information about specific registry items including the name, description, type and files content.
Get item examples from registries
Find usage examples and demos with their complete code.
Get add command for items
Get the shadcn CLI add command for specific items in a registry.
Get audit checklist
Make sure to run the tool after all required steps have been completed.
Control
What Runlayer can see and stop in Codex
Some controls apply to every client at the gateway. Others depend on what Codex exposes to Runlayer.
Gateway policy (available)
Every shadcn/ui call from Codex passes through Runlayer, where your policies can allow, alert, mask, or block it.
Audit trail (available)
Each call is recorded with the user, Codex as the client, the tool, and the policy and scanner decisions.
Client hooks (available)
Capture supported prompts, reasoning, local and MCP tool calls, responses, and scanner decisions in real time.
Stop a call before it runs (available)
Runlayer can deny a tool call or permission request before Codex runs it.
Block output after it runs (available)
Runlayer can block a tool’s output before Codex’s model sees it.
Redact output in place (not available)
Codex cannot take masked output, so Runlayer can block a tool’s output but not mask it. The gateway still applies policy to the call.
Frequently asked questions
Connect more
