Connect LaunchDarkly to Codex
Give Codex governed access to LaunchDarkly’s 141 tools through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add LaunchDarkly to Codex in four steps
Admins approve the server once. Everyone in Codex then gets it through the same governed connection.
- 1
Approve LaunchDarkly in Runlayer
Add LaunchDarkly from the catalog and choose who can use it and which of its tools are allowed.
- 2
Connect Codex to Runlayer
Runlayer’s CLI adds the Runlayer Plugin to Codex’s local plugin marketplace, and users then enable it in Codex. With direct tool listing turned on for your deployment, LaunchDarkly’s 141 tools show up in Codex’s own tool list (Codex 0.122 or newer, installed through the Runlayer CLI).
Codex setup guide - 3
Sign in to LaunchDarkly
An admin adds LaunchDarkly credentials to Runlayer once. They never sit in the client’s configuration.
- 4
Use LaunchDarkly from Codex
LaunchDarkly’s approved tools appear in Codex. Every call is checked against policy and recorded.
Tools
141 LaunchDarkly tools in Codex
Runlayer policy decides which of these Codex users can call.
Apply agentcontrol config approval
Apply an already-approved AgentControl Config approval request.
Apply approval request
Apply an already-approved flag approval request.
Archive flag
Archive a feature flag (reversible).
Check flag rollout complete
Check whether a feature flag is fully rolled out to a single deterministic variation across all traffic-bearing environments.
Check removal readiness
Detailed safety check before removing a feature flag.
Clone agentcontrol config variation
Clone an existing AgentControl Config variation with selective overrides.
Copy flag config
Copy a flag's targeting configuration from one environment to another.
Create agent graph
Create a new agent graph in a project.
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 LaunchDarkly 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
