"Chinese greeting or conversation starter" matching MCP servers:

Scaffold and audit Starter Series projects — MCP server, Claude Code skill, and CLI in one package.

Enables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.

A minimal MCP server that provides a single 'hello' tool returning a greeting message, deployable on Render.

MCP server for parsing Chinese fuzzy time expressions (e.g., '昨天', '下午3点', '中秋节') into standard datetime formats.

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.

A TypeScript starter template for MCP servers with CI/CD, OIDC npm publishing, and zero-secret setup.

Enables git-branch-style A/B experimentation for long-running tasks, allowing users to create, compare, promote, discard, or roll back parallel conversation branches via MCP tools.

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

A local MCP server that brings Chinese NLP capabilities to AI agents and IDEs. It provides four tools: Chinese word segmentation (jieba), pinyin conversion (pypinyin), TF-IDF keyword extraction, and custom sensitive-word detection (Aho-Corasick). All processing runs locally over stdio, with zero network requests and no built-in sensitive-word dictionary — users supply their own word lists. Install

Local, zero-token event triggers for Claude Code, Codex, OpenCode and ZCode: when CI fails, a training run finishes, a service goes down or NVDA crosses your price, your agent wakes up in your conversation—even if closed.

Enables AI assistants to automatically log and manage conversation history with developers in structured markdown format. Provides powerful search and context suggestions to help AI understand project history and maintain continuity across sessions.

mcp-starter is a secure, starter framework for building MCP servers with JWT-based authentication, multi-tenant enforcement, and schema validation. Built with Node.js and Docker

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 production-grade MCP starter server in TypeScript with example tools, resources, and integration tests. It provides a clean, extensible foundation for building custom MCP servers.

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.

A starter template for building single-client MCP servers that expose existing REST APIs, deployable via stdio in customer-controlled environments. It provides a structured foundation with validated config, error handling, write authorization, and a mock upstream for local development.

A minimal TypeScript MCP starter server that counts words and characters, ready to extend with custom tools.

Enables AI models to use custom tools defined in TypeScript — such as launching applications on the user's computer, reading notes, or calling APIs — exposed over the Model Context Protocol. Includes minimal example tools (current time, greeting, listing and opening installed apps) and connects to clients like opencode, Claude Desktop, or Cursor.

A minimal MCP server demonstrating tools, resources, and prompts for managing notes, with a simple notes app that supports adding, listing, deleting notes and summarizing them.

Enables Claude-compatible clients to search a bundled help center with pagination, draft validated support tickets, read documentation resources as Markdown, and use a reusable documentation-explanation prompt. It can run over stdio or streamable HTTP and serves as a configurable starting point for custom MCP servers.

Starter kit for small businesses: A2A agent card, MCP server card, minimal example MCP server (tools: leistungen, anfrage_anlegen) and validator. Python standard library only, MIT, docs in English and German.

This server provides a minimal template for creating AI assistant tools using the ModelContextProtocol, featuring a simple 'hello world' tool example and development setups for building custom MCP tools.

A foundation for building custom local Model Context Protocol (MCP) servers that provide tools accessible to AI assistants like Cursor or Claude Desktop.

A starter template for building MCP servers that enable AI assistants to interact with custom tools and data.

A minimal, production-ready starter for building Model Context Protocol servers in TypeScript, supporting both stdio and streamable HTTP transports with optional bearer-token auth.

An Express + TypeScript starter for building stateless MCP servers with explicit, typed application state, featuring a shopping-cart domain example and support for multiple state store adapters.

A production-minded Python starter for exposing typed tools over the Model Context Protocol with FastAPI.

Starter kit for building stateless MCP servers using the 2026 spec, enabling horizontal scaling without session affinity.

A production-shaped starter for putting an MCP server in front of an existing app, with OAuth and enterprise SSO handled through Clerk, enabling AI assistants to act on your product on behalf of logged-in users.