Get started with Unstructured Transform for the IBM Bob Shell

Requirements

Before you begin, you must have the following:

An IBM Cloud account. To see if you have an account, log in to your IBM Cloud account. Create an IBM Cloud account.
An IBM Bob plan. To see if you have a plan, use the IBMid for your IBM Cloud account to log in to IBM Bob.
The IBM Bob Shell installed on your local development machine. Install the IBM Bob Shell.
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 used the IBM Bob IDE to install the Transform MCP server, it could already be available to you in the IBM Bob Shell. If so, you can skip ahead to parse your source files. To see if it is, run one of the following commands:
- From outside of an IBM Bob Shell session: bob mcp list
- From within an IBM Bob Shell session: /mcp list
If the Transform MCP server is installed, you will see unstructured-transform in the list.

Install the Transform MCP server

You should be able to instruct the IBM Bob Shell to install the Transform MCP server by asking the IBM Bob Shell the following:

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

During this process, the IBM Bob Shell will open a browser window where you sign in to Transform to complete authentication. If you do not have a Transform account, click Register and then follow the on-screen directions to finish authenticating. Once authenticated, close the browser and return to the IBM Bob Shell.If this does not work, to install the Transform MCP server manually, complete the following steps.

If you were able to successfully install the Transform MCP server by using the preceding prompt, skip ahead to parse your source files.

Open the IBM Bob Shell’s mcp.json settings file in a text editor. This file is typically located at:
- For macOS and Linux: ~/.bob/settings/mcp.json (global) or .bob/mcp.json (within an individual project)
- For Windows: %APPDATA%\Bob\settings\mcp.json (global) or .bob\mcp.json (within an individual project)

Add the following entry to the mcpServers object:

{
  "mcpServers": {
    "unstructured-transform": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.transform.unstructured.io"],
      "alwaysAllow": [
        "request_file_upload_url",
        "start_transform_job",
        "check_job_status",
        "get_job_results",
        "start_extraction_job",
        "suggest_extraction_schema_for_file",
        "get_instructions"
      ],
      "disabled": false
    }
  }
}

Save and close the mcp.json file.
Start an IBM Bob Shell session by running the bob command.
If prompted, log in to Bob with your IBM Cloud account.
A web browser tab will appear, prompting you to authenticate with Transform. If you do not have a Transform account, click Register and then follow the on-screen directions to finish authenticating.
To verify that you are connected, run the /mcp command. The unstructured-transform MCP server should show a green circle icon and Ready.
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 IBM Bob Shell about these limits. Because of this, the IBM Bob Shell should notify you whenever it encounters a file that exceeds 50 MB in size. Also, the IBM Bob Shell 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.

From your terminal, in your IBM Bob Shell session, switch to the folder on your local machine that stores 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.
As needed, adapt the phrase in this project in the preceding prompt to indicate a more specific project folder. Also, as needed, guide the IBM Bob Shell 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.

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?