Skip to main content

​
Requirements

Before you begin, you must have the following:

​
Install the Transform MCP server

Transform connects to Gumloop as a custom MCP server. You sign in with your Unstructured account through OAuth, so there is no key to paste.
  1. Go to your Gumloop Connectors page.
  2. Click Add Connector, search for mcp server, and then, next to MCP Server, click Add.
  3. In the Connect MCP Server dialog, for MCP Server URL, enter https://mcp.transform.unstructured.io/.
  4. Click Connect. When prompted, sign in with your Unstructured account to authorize the connection.
  5. The connector shows Connected as a custom MCP. Transform is ready for your agents and workflows.
To confirm the connection, add an Agent node, attach Transform, and ask it to list available tools. If Transform’s tools do not appear, click Refresh next to the connector to refresh the list.

​
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.
To parse files with Transform in a Gumloop agent:
  1. In a Gumloop workflow, add an Agent node, and then attach the Transform connector to it.
  2. Enter a prompt that tells the agent to parse a file. For example:
  3. The agent calls Transform, waits for the job to finish, and returns the structured output. Route this output into a spreadsheet, database, or vector store downstream.

​
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:
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

​
Questions? Need help?