hister
Your own search engine
Hister is a private, self-hosted search engine that indexes visited web pages and local files, exposing search capabilities through a web interface, terminal, and MCP server. It enables AI assistants to search through your personal browsing history and document archive using full-text and optional semantic search. Browser extensions automatically capture visited pages, while the MCP integration lets agents query your indexed content directly. The system prioritizes privacy by running entirely on your own infrastructure with no mandatory cloud services.
Key Features
Use Cases
- 01Let AI assistants search your browsing history and visited pages when answering questions
- 02Build a searchable personal knowledge base from websites you've read and files you've saved
- 03Find information from web pages you visited weeks or months ago without bookmarking
- 04Enable Claude or other MCP clients to retrieve context from your previously visited documentation
- 05Create a team knowledge repository on a shared server with per-user document isolation
- 06Combine semantic and full-text search to find documents by meaning rather than exact keywords
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.
hister — FAQ
What is Hister MCP server?+
Hister is a self-hosted search engine that indexes web pages and local files, providing an MCP server interface so AI assistants can search through your personal document archive. It runs locally or on your own infrastructure without requiring cloud services.
How do I install Hister MCP server?+
Download the binary for your platform from the GitHub releases page, make it executable (on Linux/macOS), and run './hister listen' to start the server. Then configure your MCP client to connect to the running Hister instance at the default port 4433.
Which AI clients work with Hister MCP server?+
Hister provides MCP server functionality that works with any MCP-compatible AI assistant, including Claude Desktop and other clients that support the Model Context Protocol.
Does Hister require API keys or external services?+
No, Hister works completely offline by default with no API keys required. Optional semantic search requires you to configure your own embeddings endpoint if desired.
Is Hister free and open source?+
Yes, Hister is licensed under AGPLv3 or later and is completely free to use. The source code is available on GitHub.
Does Hister send my browsing data to external servers?+
No, Hister has no telemetry and sends indexed content only to the Hister server you configure (typically localhost). All data stays on infrastructure you control unless you explicitly enable optional semantic search with a remote embeddings endpoint.
How do I install hister?+
Open the source repository on GitHub and follow its README. hister is a mcp server — MCP Agents Market links you directly to the official repo.
Is hister free?+
hister is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.