"Chinese greeting or conversation starter" matching MCP servers:

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

MCP server that provides OpenRouter model pricing data, enabling price lookups, trending/cheapest lists, and model searches without an API key.

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

Enables AI agents to pay-per-call for Cloudflare Worker APIs using USDC micropayments, with automatic MCP tool discovery and Bazaar listing.

Enables building ChatGPT apps with custom UI widgets via a minimal Node.js MCP server, allowing tools to return structured content rendered in an iframe widget.

Enables detection of AI-generated content in images, videos, audio, and text via the AI or Not API. Supports media analysis tools for deepfakes, synthetic voices, and AI-written text.

Provides a TypeScript scaffolding that auto-loads drop-in tools, resources, and prompts, and serves them to MCP-compatible clients over stdio or streamable HTTP.

Framework for building bioengineering automation tools that AI assistants can call via the Model Context Protocol, handling server registration and tool discovery automatically.

Enables MCP-compatible agents to access KaiRouter's video generation API, providing tools to list available video models, generate videos (text-to-video or image-to-video) asynchronously, check job status, and list recent jobs.

MCP server for audio transcription using OpenRouter models, supporting verbatim, cleaned, and custom transcription modes.

Turns any SpringDoc-powered Spring Boot API into a production-ready MCP gateway, exposing existing controllers as safe MCP tools with discovery, validation, response shaping, and workflow orchestration.

Connects Figma designs to React components using your actual component library, enabling AI tools to generate production-ready code with proper imports.

Enables Claude Code agents and subagents to get an independent read-only review of their changes from OpenAI Codex and to continue that same Codex conversation later for re-checks. Runs each request in an isolated CODEX_HOME so those threads stay separate from the Codex desktop app, supporting parallel callers and per-call model, effort, sandbox, and timeout settings.

Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.

Turns a YouTube link into a readable, timestamped Markdown transcript by preferring existing subtitles and falling back to local Whisper transcription, with optional Traditional-to-Simplified Chinese conversion and Obsidian-friendly output.

An MCP server that seats multiple LLMs as a council, letting your assistant query them in parallel or in sequence, relay answers for cross-critique, and merge conclusions within one conversation.

A session-scoped memory layer for LLMs that enables AI assistants to explicitly store and retrieve notes, decisions, and context within a single conversation, ensuring focus without cross-session data contamination.

Bazi (Four Pillars) charting MCP server with true solar time correction and multilingual output in Chinese, English, Japanese, and Korean.

Image generation for Claude Code, Claude Desktop and any MCP client, using your existing ChatGPT subscription. Drives the already-signed-in Codex desktop app over the Chrome DevTools Protocol - no API key, and no Codex agent quota. Supports iterative refinement through a reusable conversation. Windows only; requires the Codex desktop app.

A Claude Code MCP server and skill that enables delegation of prompts to agy (Antigravity/Gemini) CLI for model queries, conversation management, authentication, and image generation.

Enables AI agents to receive a structured verdict on whether a UI component need can be satisfied by existing shadcn/ui or 21st.dev components or requires a custom build, with coverage scoring against real component evidence and a Mobbin reference when needed.

Enables coding agents to submit their original request, proposed plan items, and observed repository conventions for per-item necessity scoring before making edits. It returns advisory keep, simplify, or review recommendations with reasons and evidence, without blocking or modifying the plan.

Enables Claude clients to score borrower default risk, explain predictions with SHAP, compare applicants, and inspect model metadata through natural conversation. Serves a trained XGBoost model locally over stdio or remotely over HTTP with API-key authentication, keeping confidence transparent by reporting which inputs fell back to training-set defaults.

Enables document parsing into structured, confidence-scored fields via the scan tool, working with any MCP host like Claude Desktop or Cursor.

Exposes Z.ai GLM models (GLM-5.3 and siblings) as callable tools within Claude Code and Claude Desktop, enabling large-context second opinions, bulk grunt work, and independent model reasoning mid-conversation.

Allows Claude Code to request an independent code review from Google Antigravity (Gemini, Claude, or GPT-OSS) via the Antigravity CLI, providing a second opinion on plans or diffs.

Enables MCP agents to evaluate content against typed questions (yes/no, choice, or score) in a single parallel call.

Exposes 120+ Chinese frontier AI models (DeepSeek, Qwen, GLM, Kimi, Seedance, MiniMax, Hunyuan, CogVideoX) as MCP tools via one OpenAI-compatible endpoint: chat, image generation, free-model list, and a live first-party price leaderboard. Zero platform fee.

A thin MCP server that delegates lightweight tasks from Claude Code or any MCP-compatible client to local or cloud LLMs via LiteLLM, supporting models like Ollama and cloud APIs as subagents.

Enables hot-swapping llama.cpp models in a running Claude Code session via launchctl or systemd, preserving conversation context across model changes.