"Tistory" matching MCP servers:

Read-only MCP bridge for searching and browsing RikkaHub app conversations through its Web API.

Provides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.

Config-driven MCP server for cross-domain full-text search across agent session logs, meeting transcripts, and notification files.

A narrative graph engine that enables LLMs to generate, track, and mutate complex fictional worlds while maintaining consistency between factions, characters, and locations. It acts as a specialized RAG framework for storytelling, allowing models to manage thousands of entities without exceeding context limits.

Enables semantic search over local AI-agent session logs (e.g., Claude Code, Hermes) using local embeddings, returning relevant chunks without exposing full transcripts.

Enables searching through vectorized Cursor IDE chat history via a FastAPI service powered by LanceDB and Ollama.

Local semantic search over Claude Code sessions and shell command history, exposed to Claude Code as an MCP tool. Everything is indexed into one vector space and runs entirely on your machine.

Enables semantic search over your Cursor IDE chat history by vectorizing prompts and storing them in LanceDB. Provides a Dockerized API to perform vector similarity searches against your chat history.

A semantic search MCP server that provides historical question-and-answer capabilities using an embedding-based retrieval system. It connects to the XiaoZhi Agent via WebSockets to query a local SQLite history database.