# Unstructured MCP server > Parse, chunk, enrich and embed documents into structured, AI-ready data for RAG, vector stores and agent memory. - Listing: https://mcp.tc/i/unstructured - Connect: use the server's own URL `https://mcp.transform.unstructured.io` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: OAuth sign-in - Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml) - Vendor: Unstructured - Homepage: - Repository: ## About Unstructured Transform turns files such as PDFs, spreadsheets, scans and emails into partitioned, enriched, chunked and embedded output. It supports more than 60 formats. You can also run schema-based extraction jobs and ask for a suggested extraction schema for a file. The server is hosted at https://mcp.transform.unstructured.io and uses streamable HTTP. Users sign in with OAuth, and an Unstructured API key sent as a Bearer token also works. Clients without native remote MCP support can connect through npx mcp-remote. ## What it can do - Request an upload URL for a file - Start a transform job to partition, enrich, chunk and embed a document - Start a schema-based extraction job on a file - Get a suggested extraction schema for a file - Check the status of a running job - Fetch the results of a finished job ## Example prompts - "Parse this PDF and split it into chunks ready for a vector store." - "Suggest an extraction schema for this invoice file." - "Extract the line items from this spreadsheet into structured data." - "Check whether my transform job has finished and get the results." ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http unstructured https://mcp.transform.unstructured.io ``` 2. Start Claude Code, type `/mcp`, pick **unstructured** and choose **Authenticate**. A browser window opens for the Unstructured sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **Unstructured** and paste this URL: ```url https://mcp.transform.unstructured.io ``` 3. Click **Add**, then **Connect**, and sign in when Unstructured asks. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://mcp.transform.unstructured.io` and click **Add**. 3. Click **Connect** and sign in when Unstructured asks. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://mcp.transform.unstructured.io` as the server URL and choose **OAuth**. ChatGPT sends you to Unstructured to sign in. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "unstructured": { "url": "https://mcp.transform.unstructured.io" } } } ``` Cursor shows **Needs login** next to the server. Click it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"unstructured","type":"http","url":"https://mcp.transform.unstructured.io"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "unstructured": { "type": "http", "url": "https://mcp.transform.unstructured.io" } } } ``` VS Code asks you to sign in the first time the server starts. ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "unstructured": { "serverUrl": "https://mcp.transform.unstructured.io" } } } ``` 2. Refresh the MCP server list in Cascade and sign in when asked. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add unstructured --url https://mcp.transform.unstructured.io codex mcp login unstructured ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.unstructured] url = "https://mcp.transform.unstructured.io" ``` ### Gemini CLI ```bash gemini mcp add --transport http unstructured https://mcp.transform.unstructured.io ``` Then, inside Gemini CLI, run `/mcp auth unstructured` to sign in. This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "unstructured": { "type": "http", "url": "https://mcp.transform.unstructured.io" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.transform.unstructured.io`. ## Details - Server version: 0.7.2 - Last checked: 2026-10-03 (reachable, asks for credentials) - Listed: 2026-10-03 - Updated: 2026-10-03 --- Source: https://mcp.tc/i/unstructured (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report