"Chinese greeting or conversation starter" matching MCP servers:

Full-text search over Claude Code conversation history using SQLite FTS5, exposing indexed transcripts as MCP tools for searching, browsing, and reading turns.

Enables transferring conversation context between different AI chats or projects with automatic server discovery and memory-based storage. Supports saving, loading, and managing conversation histories in a human-readable Markdown format.

Provides evidence-backed decision support for Codex by indexing local task history, assigning independent councillors, and verifying historical claims against local evidence.

A CLI-based MCP server for managing conversation sessions, history, and multi-language support, enabling creation, switching, deletion of sessions, saving and searching messages, and exporting data.

A local MCP server that indexes and searches your Claude Code conversation history with both keyword and semantic search, fully private and running locally.

A Model Context Protocol server implementation that provides a standardized interface for applications to interact with OpenRouter's language models through a unified conversation management system.

Enables intelligent conversation management with 4 AI agents that provide semantic analysis, pattern discovery, automatic documentation, and relationship mapping. Logs and analyzes Claude conversations with 70% token optimization and multi-language support.

Enables comprehensive search and analysis of Claude Code conversation history using full-text search, optional semantic vector search, and conversation management tools. Provides fast SQLite-based indexing with role-based filtering, project organization, and hybrid search capabilities combining keyword and semantic matching.

Enables Claude Code to search, browse, and read its own past conversation history across all projects using BM25 keyword search.

Enables searching all Claude Code conversations across projects using natural language queries and instantly provides resume commands to continue discussions.

A minimal MCP server with calculator and memory store tools, ready to use with Claude Desktop and Claude Code.

Scoped, low-latency persistent memory layer for AI agents, Cursor, and Claude Code over Model Context Protocol with sub-50ms hybrid search.

An MCP server that provides searchable local storage for Claude conversation history, featuring automatic topic extraction and weekly insight summaries. It enables Claude to retrieve context from past sessions through full-text search and organized file storage.

A local MCP server providing general utility tools, persistent note storage, and keyword-searchable knowledge base via Streamable HTTP, enabling multiple agents to share the same data.

Enables AI agents to inspect ontology schemas, search typed objects, and execute read-only SPARQL queries against an RDF triple store.

Enables Claude and Cursor to access agent memory, shared knowledge graphs, and decision audit through MCP.

Enables agents to create, list, and keyword-search scoped in-memory notes for user IDs over stdio, with state preserved between calls.

Gives AI agents persistent memory with bi-temporal tracking, automatically extracting entities from natural language and enabling time-travel queries to understand facts as they existed at any point in history.

Provides tools for Bazi (Chinese astrology) chart calculation and analysis, enabling LLMs to generate accurate birth charts, determine patterns, and answer follow-up questions based on actual calculations rather than model knowledge.

Searches your local Claude Code conversation history to recall and resume past solutions.

Automatically saves and retrieves AI conversation sessions to maintain context continuity, preventing re-explaining architecture decisions.

Local-only MCP server for saving and restoring conversation context across AI agent sessions using JSON files on disk.

Enables long-horizon AI agents to replace append-only conversation history with a formal, bounded state tuple, supporting state initialization, step execution with transactional rollback, observation injection, and session inspection.

A knowledge-based MCP server for Ozon sellers, enabling AI agents to search a 42-lesson Chinese operations playbook and discover/call over 460 Seller and Performance API methods for real business actions.

A server that summarizes and records conversation key points, supporting adding summaries and viewing history.

Exposes tools that let an agent search a local Markdown-based memory store, fetch full cards by id, write new knowledge cards that are indexed immediately, and inspect or rebuild the SQLite index. All retrieval runs locally over Chinese-friendly full-text search with graded exact/prefix matching, so agents without a memory system can recall prior notes while existing Markdown files stay read-only.

Search past OpenCode conversation history before starting new work on a module or file, via a local read-only FTS5 index built from OpenCode's own SQLite database. No network calls, fully local. 7 tools for keyword search, file lookup, and session browsing.

Provides brain-inspired long-term memory for MCP clients, enabling persistent user understanding across sessions with Chinese-optimized hybrid retrieval and evolving user profiles.

A timestamped audit trail for every AI conversation — stored locally, owned by you.

A personal memory MCP server that ingests AI agent conversation logs from multiple platforms into a searchable PostgreSQL+pgvector database, enabling cross-session recall of past reasoning and decisions.