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.
- Codex Desktop installed on your local development machine. Install Codex Desktop.
- Node.js installed on your local development machine. To see if it is, in your terminal, run
node -vornode --version. Install Node.js.
Install the Transform MCP server
- Start Codex Desktop.
- In Codex Desktop, on the sidebar, click your user icon, and then click Settings.
- On the sidebar, under Integrations, click MCP servers.
- Click Add server.
-
For Name, enter
transform - Leave STDIO selected.
-
For Command to launch, enter
npx -
For Arguments, enter the following arguments, one at a time, clicking Add argument to add the next argument in sequence:
a.
-y
b.mcp-remote
c.https://mcp.transform.unstructured.io
- Leave all of the other settings untouched, and then click Save.
- Stop Codex Desktop.
-
In your terminal, authenticate with the Transform MCP server:
A web browser tab will appear, prompting you to authenticate with Transform. Follow the on-screen directions to finish authenticating.
-
After you authenticate, back in your terminal, press
Ctrl + Cto exit and return to your terminal prompt. - Restart Codex Desktop.
- The Transform MCP server is ready for you to start using.
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.
- After you install the Transform MCP server and restart Codex Desktop, select the project containing the folder on your local machine that stores the files you want Transform to parse.
-
In the Do anything box, enter the following prompt:
As needed, adapt the phrase
in this projectin the preceding prompt to indicate a more specific project folder. Also, as needed, guide Codex Desktop 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 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 general questions about Unstructured products and pricing, email Unstructured Sales at sales@unstructured.io.
- For technical support, request support.

