Get started with Unstructured Transform for Google Antigravity

Connect the server once and it works in all three clients: Antigravity 2.0, Antigravity CLI, and Antigravity IDE. The three Antigravity clients share the same configuration files and customization discovery engine.

You might have to close and restart the other clients for them to register the new connection.

Requirements

A Google Account. To see if you have an account, sign in to your Google Account. To create a Google account, go to the Google Account sign-in page and click Use another account, then Create account.
Each Antigravity client you want to use installed on your local development machine. Install Antigravity clients. To see if Antigravity CLI is installed, in your terminal, run agy --version.
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.
If you installed the Transform MCP server for use with any Antigravity client, you already have access to it in the other Antigravity clients.
To see if Antigravity is already connected to Transform
To determine if your Antigravity client is already connected to Transform:
- In Antigravity 2.0, click Settings, then Customizations, and look for unstructured-transform under Installed MCP Servers. Click Refresh if the list is out of date.
- In the Antigravity CLI, run the command /mcp and see if unstructured-transform is listed.
- In the Antigravity IDE, click Antigravity - Settings, then Advanced Settings, then Customizations, and look for unstructured-transform under Installed MCP Servers. Click Refresh if the list is out of date.

Install the Transform MCP server

You should be able to instruct your Antigravity client to install the Transform MCP server by asking it:

Install the Unstructured Transform MCP server by using these instructions: 
https://docs.unstructured.io/transform/get-started/antigravity.md

If the prompt worked, you’re ready to parse your source files. Otherwise, install the server manually.

Install the Transform MCP server manually

Open the MCP configuration file

Open Antigravity’s mcp_config.json settings file in a text editor. Antigravity stores this file at:

For macOS and Linux: ~/.gemini/config/mcp_config.json
For Windows: %USERPROFILE%\.gemini\config\mcp_config.json

Add the Transform MCP server entry

Add the following entry to the mcpServers object, and then save and close the file:

{
  "mcpServers": {
    "unstructured-transform": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.transform.unstructured.io"]
    }
  }
}

Authenticate with the Transform MCP server

From your terminal, authenticate with the Transform MCP server:

npx -y mcp-remote https://mcp.transform.unstructured.io

A web browser tab will appear, prompting you to authenticate with Transform. Follow the on-screen directions to finish authenticating. After you authenticate, return to your terminal and press Ctrl + C to exit.

Start Antigravity

Start Antigravity 2.0, Antigravity IDE, or start an Antigravity CLI session by running the agy command.

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 your Antigravity client about these limits. Because of this, your Antigravity client should notify you whenever it encounters a file that exceeds 50 MB in size. Also, Antigravity 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.

Antigravity 2.0
Antigravity CLI
Antigravity IDE

Install the Transform MCP server and start Antigravity 2.0. Then select the project that holds the files you want Transform to parse.
In the Ask anything box, 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.
Optionally, adapt the phrase in this project to name a more specific folder, or tell Antigravity where to write Transform’s output. Transform parses your input files and delivers its results to you as a set of output files, one output file per input file.

Install the Transform MCP server, then start an Antigravity CLI session. In your terminal, switch to the folder that holds the files you want Transform to parse.
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.
Optionally, adapt the phrase in this project to name a more specific folder, or tell Antigravity where to write Transform’s output. Transform parses your input files and delivers its results to you as a set of output files, one output file per input file.

Install the Transform MCP server and start Antigravity IDE. Then select the project that holds the files you want Transform to parse.
In the Agent pane, click the plus icon (New conversation), and then 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.
(Optional) Adapt the phrase in this project to name a more specific folder, or tell Antigravity where to write Transform’s output. Transform parses your input files and delivers its results to you as a set of output files, one output file per input file.

Extract structured data

If you want to pull specific fields from your files, instead of converting the files in full, ask for an extraction. To determine what structured data Transform can extract from your files, use a prompt similar to the following:

Use the Unstructured Transform MCP server to extract structured data from these files.

I don't have a schema — suggest one based on what's in the document, show it to me, and then run the extraction with it.

Your tool parses each file first, then extracts the field values from the parsed element JSON; this is because the Transform MCP extraction tools read a file’s parsed output, rather than the raw file itself. Transform returns results as JSON matching the schema, wrapped with the source filename so you can tell a batch apart. If you know the specific fields you want, include them in your prompt to guide Transform in extracting just the information that’s important to you. For more information, including prompting patterns and performance considerations, see Structured data extraction.

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.

​Requirements

​Install the Transform MCP server

​Parse your source files

​Extract structured data

​Next steps

​Questions? Need help?

Requirements

Install the Transform MCP server

Parse your source files

Extract structured data

Next steps

Questions? Need help?