Connect Playwright to Codex
Give Codex governed access to Playwright’s 27 tools through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add Playwright to Codex in four steps
Admins approve the server once. Everyone in Codex then gets it through the same governed connection.
- 1
Approve Playwright in Runlayer
Add Playwright 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 Playwright, which runs on the user’s machine. Auto Sync can then write Playwright into Codex on macOS, Windows, and Linux.
Codex setup guide - 3
Sign in to Playwright
Sign in the way Playwright requires. Runlayer holds the credentials so they stay out of the client’s configuration.
- 4
Use Playwright from Codex
Playwright’s approved tools appear in Codex. Every call is checked against policy and recorded.
Tools
27 Playwright tools in Codex
Runlayer policy decides which of these Codex users can call.
Browser click
Perform click on a web page
Browser close
Close the page
Browser console messages
Returns all console messages
Browser drag
Perform drag and drop between two elements
Browser drop
Drop files or MIME-typed data onto an element, as if dragged from outside the page.
Browser emulate media
Emulate CSS media features for the page, for example switch between the light and dark color scheme.
Browser evaluate
Evaluate JavaScript expression on page or element
Browser file upload
Upload one or multiple files
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 Playwright 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