Connect Profound to Codex
Give Codex governed access to Profound’s 61 tools through Runlayer, with identity, policy, scanning, and audit on every call.
Set up
Add Profound to Codex in four steps
Admins approve the server once. Everyone in Codex then gets it through the same governed connection.
- 1
Add Profound to Runlayer
Profound isn’t in the Runlayer catalog yet, so an admin adds it by its MCP server URL.
Adding a connector manually - 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, Profound’s 61 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 Profound
Sign in the way Profound requires. Runlayer holds the credentials so they stay out of the client’s configuration.
- 4
Use Profound from Codex
Profound’s approved tools appear in Codex. Every call is checked against policy and recorded.
Tools
61 Profound tools in Codex
Runlayer policy decides which of these Codex users can call.
Add knowledge base document
Add ONE new document (inline markdown text) to a knowledge base.
Archive project
Preview or archive (retire) a project — set it aside without deleting it.
Create agent definition
Create a draft agent definition — preview first, then apply on confirmation.
Create doc
Create a new document in the Profound platform from content you have written.
Create project task
Preview or add a task ("play") to a project.
Create prompts
Create one or more prompts in a category.
Get agent
Get details of an agent, including its input_schema.
Get agent definition
Read back an agent's full workflow graph so you can copy and edit it.
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 Profound 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