Hyper-Extract
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
Hyper-Extract MCP server enables AI assistants to transform unstructured documents into structured knowledge graphs, hypergraphs, and other semantic formats through the Model Context Protocol. This building block exposes read-only tools that let MCP clients query extracted knowledge, browse 80+ domain-specific templates, perform RAG-powered searches, and export results to Obsidian vaults. Built on top of the Hyper-Extract CLI framework, it bridges LLM-powered knowledge extraction with AI assistants, supporting multiple providers including OpenAI, Anthropic Claude, DeepSeek, Alibaba Bailian, and local vLLM deployments.
Key Features
Use Cases
- 01Enable Claude Desktop to extract entity-relationship graphs from academic papers and earnings reports
- 02Let AI assistants query structured knowledge extracted from legal documents with source provenance
- 03Build domain-specific knowledge bases from medical records using pre-built TCM and healthcare templates
- 04Create searchable biography graphs from unstructured text that assistants can query via natural language
- 05Export extracted knowledge to Obsidian for human review while maintaining MCP access for AI agents
- 06Deploy on-premise knowledge extraction with local vLLM models for privacy-sensitive documents
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.
Hyper-Extract — FAQ
What is the Hyper-Extract MCP server?+
It's an MCP server that exposes knowledge extraction capabilities to AI assistants through the Model Context Protocol. The server provides tools for searching extracted knowledge bases, browsing templates, performing RAG queries, and exporting results, enabling assistants like Claude Desktop to work with structured semantic data extracted from documents.
How do I install the Hyper-Extract MCP server?+
Install the hyperextract package with MCP extras using pip, configure your LLM provider and API key, then add the he-mcp command to your MCP client's configuration file. For Claude Desktop, this means editing the claude_desktop_config.json file to include the server definition with the appropriate command and arguments.
Which AI clients work with this MCP server?+
Any MCP-capable client works with Hyper-Extract, including Claude Desktop and other assistants that implement the Model Context Protocol. The README specifically mentions Claude Desktop and IDE agents as target clients.
Do I need API keys to use Hyper-Extract?+
Yes, you need an API key for your chosen LLM provider (OpenAI, Anthropic, DeepSeek, or Alibaba Bailian) and typically a separate embedding API key unless using a provider that offers both. Local vLLM deployments require GPU hardware but no external API keys.
Is the Hyper-Extract MCP server free?+
The software is open source under Apache 2.0 license and free to use. However, you'll incur costs from your chosen LLM provider—DeepSeek is noted as the most cost-effective at roughly $0.001-0.005 per page versus OpenAI at $0.01-0.05 per page.
What are the prerequisites for running this server?+
You need Python 3.11 or higher and access to an LLM provider that supports function calling (OpenAI, Anthropic, DeepSeek, Bailian, or a local vLLM instance). An OpenAI-compatible embedding API is also required for semantic search functionality.
How do I install Hyper-Extract?+
Open the source repository on GitHub and follow its README. Hyper-Extract is a mcp server — MCP Agents Market links you directly to the official repo.
Is Hyper-Extract free?+
Hyper-Extract is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.