Skip to main content

Connect Planhat to Codex

Give Codex governed access to Planhat’s 10 tools through Runlayer, with identity, policy, scanning, and audit on every call.

Set up

Add Planhat to Codex in four steps

Admins approve the server once. Everyone in Codex then gets it through the same governed connection.

  1. 1

    Add Planhat to Runlayer

    Planhat isn’t in the Runlayer catalog yet, so an admin adds it by its MCP server URL.

    Adding a connector manually
  2. 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, Planhat’s 10 tools show up in Codex’s own tool list (Codex 0.122 or newer, installed through the Runlayer CLI).

    Codex setup guide
  3. 3

    Sign in to Planhat

    Sign in the way Planhat requires. Runlayer holds the credentials so they stay out of the client’s configuration.

  4. 4

    Use Planhat from Codex

    Planhat’s approved tools appear in Codex. Every call is checked against policy and recorded.

Tools

10 Planhat tools in Codex

Runlayer policy decides which of these Codex users can call.

  • Create document

    Create a new document (page) in Planhat.

  • Create model record

    MODEL: "Company", PARAMETERS: {"name": "Acme Corp", "domain": "acme.com"}

  • Delete model record

    Delete existing record.

  • Get document

    Retrieve a document (page) by its ID, including its full content.

  • Get model action parameters

    Returns field metadata (names, types, required flags) for a data model.

  • Get model record

    Get single record by ID.

  • List model records

    MODEL: "Company", LIMIT: 20

  • Search documents

    Search documents (pages) by text.

See all 10 Planhat tools

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 Planhat 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

Find another combination