unstructured
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning
Unstructured Transform MCP server enables AI agents to convert over 60 document formats—including PDFs, Word documents, emails, and scanned images—into structured, agent-ready data. The server provides production-grade document parsing, enrichment, chunking, and embedding capabilities directly within an agent's workflow. Developers can integrate it with MCP-compatible clients like Claude Code, Cursor, or Codex CLI to process documents through natural language instructions. The service includes 15,000 free pages monthly with transparent per-page pricing thereafter, making it practical for both prototyping and production document-processing pipelines.
Key Features
Use Cases
- 01Extracting structured data from contracts, invoices, and legal documents for agent analysis
- 02Preparing document collections for vector database indexing and semantic search
- 03Converting scanned historical documents into machine-readable text for research applications
- 04Processing email attachments and multi-format documents in customer support workflows
- 05Building document Q&A systems by chunking and embedding PDFs and Word files
- 06Automating data extraction from tables and forms across mixed document types
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
unstructured — FAQ
What is Unstructured Transform MCP server?+
It's an MCP server that gives AI agents the ability to convert over 60 document formats into structured data through parsing, enrichment, chunking, and embedding capabilities. Agents can process files by simply referencing them and describing their needs in natural language.
How do I install the Unstructured Transform MCP server?+
Add the server to your MCP client's configuration using the CLI 'mcp add' command or by editing the client's config file. After authenticating once when prompted, the Transform tools become available to your agent immediately.
Which AI clients work with this MCP server?+
The server works with virtually any MCP-compatible client including Claude Code, Cursor, Codex CLI, and other MCP host applications.
Do I need an API key or account?+
Yes, you need to authenticate once when your client prompts you during initial setup. After signing in, the Transform tools remain available for subsequent agent sessions.
Is the Unstructured Transform MCP server free?+
It includes 15,000 free pages per month. Additional pages are billed at 3 cents per page after the free tier is exhausted.
What document formats are supported?+
The server supports over 60 file types including PDFs, Word documents, PowerPoint presentations, Excel spreadsheets, HTML, emails, images, scanned documents, and many more formats commonly used in business and research.
How do I install unstructured?+
Open the source repository on GitHub and follow its README. unstructured is a mcp server — MCP Agents Market links you directly to the official repo.
Is unstructured free?+
unstructured is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.