Unstructured Transform MCP server installation for the Gemini CLI

​

Requirements

You will need:

• The Gemini CLI installed on your local development machine. To see if it is, in your terminal, run gemini --version. Install the Gemini CLI.
• The Gemini CLI authenticated with a model, using either a Google account login or a Gemini API key. Get a Gemini API key.
• Node.js installed on your local development machine. To see if it is, in your terminal, run node -v or node --version. Install Node.js.

​

Install the Transform MCP server

There are two ways to install the Transform MCP server into the Gemini CLI. Installing the Unstructured extension is recommended, because it also ships the guidance that helps the CLI drive the parsing flow correctly. If you would rather configure the server by hand, use the manual steps instead.

​

Option 1: Install the Unstructured extension (recommended)

1. In a terminal window, install the extension from its GitHub repository:
   gemini extensions install https://github.com/Unstructured-IO/transform-gemini-extension
   
   If the CLI prompts you to acknowledge that you are installing a third-party extension, confirm the prompt to continue.
2. Authenticate with the Transform MCP server:
   npx -y mcp-remote https://mcp.transform.unstructured.io
   
   A browser tab appears, prompting you to authenticate with Transform. Follow the on-screen directions to finish authenticating. Your credentials are cached locally, so you only need to do this once.
3. After you authenticate, back in your terminal, press Ctrl + C to exit and return to your terminal prompt.
4. Start a Gemini CLI session by running the gemini command.
5. Confirm that the server is connected by running /mcp in the session. The transform server should show as connected and list four tools: request_file_upload_url, transform_files, check_transform_status, and get_transform_results.

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

​

Option 2: Configure the server manually

1. Open the Gemini CLI’s settings.json settings file in a text editor. This file is typically located at:
   • For macOS and Linux: ~/.gemini/settings.json
   • For Windows: %USERPROFILE%\.gemini\settings.json
2. Add the following entry to the mcpServers object:
   {
     "mcpServers": {
       "transform": {
         "command": "npx",
         "args": ["-y", "mcp-remote", "https://mcp.transform.unstructured.io"]
       }
     }
   }
   
   Use the server URL exactly as shown. Do not add /mcp or /sse to the end of the URL.
3. Save and close the settings.json file.
4. In a terminal window, authenticate with the Transform MCP server:
   npx -y mcp-remote https://mcp.transform.unstructured.io
   
   A browser tab appears, prompting you to authenticate with Transform. Follow the on-screen directions to finish authenticating. Your credentials are cached locally, so you only need to do this once.
5. After you authenticate, back in your terminal, press Ctrl + C to exit and return to your terminal prompt.
6. Start a Gemini CLI session by running the gemini command.

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.

The Transform MCP server is designed to notify the Gemini CLI about these limits. Because of this, the Gemini CLI should notify you whenever it encounters a file that exceeds 50 MB in size. Also, the Gemini 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 Gemini 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 Gemini 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 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.