memex-targeted-search-server

memex-targeted-search-server

3.2

If you are the rightful owner of memex-targeted-search-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Memex Targeted Search Server is a Model Context Protocol (MCP) server designed to provide efficient and targeted search capabilities across Memex conversation history and project files.

The Memex Targeted Search Server is a powerful tool that enables AI agents to perform targeted searches through extensive conversation histories and project files. With over 952 conversation files and 516 project directories, the server offers a comprehensive search experience. It is designed to handle various file types and technologies, ensuring that users can find the information they need quickly and efficiently. The server's smart context management features prevent context overload by returning only the most relevant snippets, and its faceted filtering allows for precise search results. Built with TypeScript and Node.js, the server leverages the MCP SDK for seamless integration and performance.

Features

  • Core Search Tools: Includes functions like `search_conversations`, `get_conversation_snippet`, `search_projects`, and `get_project_overview` for comprehensive search capabilities.
  • Smart Context Management: Returns targeted snippets and limits search scope to prevent context explosion.
  • Faceted Filtering: Supports filtering by dates, projects, and file types for precise search results.
  • Relevance Scoring: Provides relevance scoring for search results to ensure the most pertinent information is highlighted.
  • Command Finder: A new feature that allows users to find specific commands, CLI usage, or code snippets from conversation history.