> ## Documentation Index > Fetch the complete documentation index at: https://docs.unstructured.io/llms.txt > Use this file to discover all available pages before exploring further. # Get started with Unstructured Transform for Visual Studio Code > Learn how to install the Unstructured Transform MCP server into Visual Studio Code. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes. ## Requirements This page describes how to use GitHub Copilot as your agent within Visual Studio Code. Before you begin, you must have the following: * Visual Studio Code. [Install Visual Studio Code](https://code.visualstudio.com/download). * A GitHub Copilot account. To verify, start Visual Studio Code, click the Copilot icon in the Visual Studio Code status bar, and then: * If you already have a Copilot subscription for your account, Visual Studio Code will use that subscription. * If you do not have a Copilot subscription yet, you will be signed up for the [Copilot Free plan](https://docs.github.com/en/copilot/concepts/billing/individual-plans) and get a monthly allowance of inline suggestions and AI credits. [Learn more about the different Copilot plans](https://docs.github.com/en/copilot/get-started/plans). * 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](https://nodejs.org/en/download). ## Install the Transform MCP server You should be able to instruct Visual Studio Code to install the Transform MCP server by asking Visual Studio Code the following: ```text theme={null} Install the Unstructured Transform MCP server by using these instructions: https://docs.unstructured.io/transform/get-started/vs-code.md ``` You can run this prompt for example from the **Chat** view in Visual Studio Code (from the main menu, click **View > Open View > Chat**.) During this process, Visual Studio Code 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 Visual Studio Code. 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](#parse-your-source-files). 1. In the Visual Studio Command Palette (from the main menu, click **View > Command Palette**), run the command `>MCP: Open User Configuration` (make sure to begin the command with `>`). 2. In the `mcp.json` file's code editor that appears, add the following entry to the `servers` object. If there are existing entries in the `servers` object, do not change or delete them: ```json theme={null} { "servers": { "unstructured-transform": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.transform.unstructured.io"] } } } ``` 3. Save and close the `mcp.json` file. 4. From your terminal, authenticate with the Transform MCP server: ```bash theme={null} npx -y mcp-remote https://mcp.transform.unstructured.io ``` 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. 5. After you authenticate, back in your terminal, press `Ctrl + C` to exit and return to your terminal prompt. 6. Start Visual Studio Code. If Visual Studio Code is already running, quit and then restart it. 7. 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](/transform/supported-file-types). * 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 Visual Studio Code about these limits. Because of this, Visual Studio Code should notify you whenever it encounters a file that exceeds 50 MB in size. Also, Visual Studio Code 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 or restart Visual Studio Code, use Visual Studio Code to open the folder that stores the files you want Transform to parse (from the main menu, click **File > Open Folder**). 2. If the **Chat** view is not visible, open it (from the main menu, click **View > Open View > Chat**.) 3. In the **Chat** view's **Describe what to build** box, enter the following prompt: ```text theme={null} Use the Unstructured Transform MCP server to parse the files in this folder. Provide the results as JSON files, one JSON file per source file. ``` As needed, adapt the phrase `in this folder` in the preceding prompt to indicate a more specific folder. Also, as needed, guide Visual Studio Code as to where to write Transform's output into the folder. 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: ```text theme={null} 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](/transform/sde). ## Troubleshooting ### Cannot find Transform MCP server connection details **Issue**: When you prompt Visual Studio Code to use the Unstructured Transform MCP server, Visual Studio Code cannot find any of the MCP server's connection details. **Cause**: Visual Studio Code attempts to find the `mcp.json` file that contains these connection details in locations such as the current folder or locally cloned repositories. However, this `mcp.json` file is typically located within these locations instead: * For macOS: `~/Library/Application Support/Code/User/mcp.json` * For Linux: `~/.config/Code/User/mcp.json` * For Windows: `%APPDATA%\Code\User\mcp.json` **Solution**: In your prompt, instruct Visual Studio Code where to find the `mcp.json` file that contains information about the Transform MCP server. For example, for macOS: ```text theme={null} Use the Unstructured Transform MCP server as specified in ~/Library/Application Support/Code/User/mcp.json to parse the files in this folder. Provide the results as JSON files, one JSON file per source file. ``` ## Next steps * [Control Transform file parsing output](/transform/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](/transform/sde): Control how the Unstructured Transform MCP server extracts and formats structured data from your files. * [Control Transform generated sample code](/transform/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](/support/request).