Unstructured Transform MCP server installation for the Codex CLI

Learn how to install the Unstructured Transform MCP server into the Codex CLI. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.

Requirements

Before you begin, you must have the following:

• A ChatGPT plan. To see if you have a plan, go to ChatGPT and click Log in. Sign up for ChatGPT.
• The Codex CLI installed on your local development machine. To see if it is, from your terminal, run codex --version. Install the Codex CLI from your terminal.

Install the Transform MCP server

You should be able to instruct the Codex CLI to install the Transform MCP server by asking the Codex CLI the following:

Install the Unstructured Transform MCP server by using these instructions: 
https://docs.unstructured.io/transform/install/codex-cli.md

If this does not work, to install the Transform MCP server manually, complete the following steps.

If you are able to successfully connect, skip ahead to parse your source files.

1. From your terminal, register the Transform MCP server’s Streamable HTTP URL:

   codex mcp add unstructured-transform \
     --url https://mcp.transform.unstructured.io
   

2. Verify that Codex lists the server:

   codex mcp list
   

3. Start a Codex CLI session, or restart an existing session. In the Codex terminal UI, enter /mcp to view active MCP servers.

4. The Transform MCP server is ready for you to start using.

Authenticate with Transform if needed

(Optional) If Transform requests authentication or you need to authenticate again, run the following command:

codex mcp login unstructured-transform

Follow the on-screen instructions to finish authenticating.

Use Transform in other Codex clients

The Codex CLI, Codex IDE extension, and ChatGPT desktop app share MCP configuration on the same Codex host. After you add Transform in the CLI, restart the ChatGPT desktop app on macOS to use it. If the app requests authentication, select Authenticate.

Parse your source files

Parsing requests have the following limits:

• Each file must be of a supported file type.
• Each file must be 50 MB or less in size.
• Each request must have 10 files or fewer.
• Only 5 requests can be running at a time.

The Transform MCP server is designed to notify the Codex CLI about these limits. Because of this, the Codex CLI should notify you whenever it encounters a file that exceeds 50 MB in size. Also, the Codex CLI should formulate strategies to send requests that are 10 files or fewer and not cause more than 5 requests to be running at a time.

1. After you install the Transform MCP server and start a Codex CLI session, from your terminal, switch to the folder on your local machine that stores the files you want Transform to parse.

2. Enter the following prompt:

   Use the Unstructured Transform MCP server to parse the files in this project.
   
   Provide the results as JSON files, one JSON file per source file.
   

   As needed, adapt the phrase in this project in the preceding prompt to indicate a more specific project folder. Also, as needed, guide the Codex CLI as to where to write Transform’s output into the project.

   Transform parses your input files and delivers its results to you as a set of output files, one output file per input file.

Next steps

• Control Transform file parsing output: Control how the Unstructured Transform MCP server instructs Transform to partition, enrich, chunk, and embed the data based on your files.
• Control Transform structured data extraction: Control how the Unstructured Transform MCP server extracts and formats structured data from your files.
• Control Transform generated sample code: Control how the Unstructured Transform MCP server generates sample curl or Python code that demonstrates how to use Transform to partition, enrich, chunk, and embed the data based on your files.

Questions? Need help?

• For technical support, request support.