Awesome - MCP - ZH is a collection of MCP (Model Context Protocol) resources tailored for Chinese users, including basic introductions, usage guides, client, server, and community resources to help users quickly get started with MCP.

A tool for querying AWS cost data and Bedrock usage logs via the MCP protocol

This project compiles a list of popular Model Context Protocol (MCP) servers based on Smithery.ai usage data. MCP is an open-source standard developed by Anthropic for establishing secure two-way connections between data sources and AI tools.

CICADA is an MCP server that provides structured code indexing for AI code assistants. Through AST-level indexing, call site tracking, and semantic search, it provides efficient context compression for Elixir, Python, and Erlang code repositories, reducing token usage and improving the quality of code understanding.

A simple MCP implementation based on the Talos SDK, used to obtain data from multiple Talos nodes, including disk, network interface, CPU, and memory usage, and supports restarting nodes.

MCP Linker is a tool that helps users quickly add Model Context Protocol servers to MCP clients. It supports clients such as Claude and Cursor and provides functions like one-click addition, favorites, and recent usage.

An enhanced MCP server that supports intelligent retrieval, combination, and management of prompts from GitHub repositories, providing advanced search, real-time synchronization, and usage analysis functions.

An MCP server based on Claude AI for optimizing programming prompts and enhancing the usage experience in AI IDEs such as Cursor.

This project is a research and documentation on the Model Context Protocol (MCP), including technical analysis, implementation solutions, usage guides, and other resources, aiming to comprehensively introduce the MCP ecosystem.

tldraw-agent is an AI-based text-to-chart generation tool that supports multiple usage methods such as command line, library, and MCP service, and can automatically generate text descriptions (such as architecture diagrams and flowcharts) into charts in PNG or SVG format.

A serverless implementation of the Model Context Protocol (MCP) based on AWS Lambda and SAM, providing two interfaces for system configuration and client usage.

An MCP server designed for the Prometheus database, supporting functions such as LLMs retrieving and analyzing metric data through tool functions, searching for metric usage, and executing complex queries.

An optimized MCP protocol web scraping server that significantly reduces the token usage of AI processing through server - side HTML to Markdown conversion and CSS selector filtering, providing efficient content extraction functions.

The Unsloth MCP Server is a server for efficiently fine-tuning large language models. Through optimized algorithms and 4-bit quantization technology, it achieves a 2-fold increase in training speed and an 80% reduction in video memory usage, supporting multiple mainstream models.

ApiFox MCP Server is an interface server based on the Model Context Protocol, used to obtain and manage ApiFox interface information. It supports both HTTP service and CLI command-line usage methods.

The project description shows how to configure Claude Desktop to integrate the Adfin MCP service, including installing the uv tool, modifying the configuration file, and usage examples.

An MCP server that can accurately calculate the number of characters, supporting multi - byte characters and multiple usage methods

An MCP server for Claude Code that achieves over 90% context compression through structured incremental snapshots, significantly saving token usage.

A service based on the Model Context Protocol (MCP) that provides search, category browsing, and usage example functions for the Lucide React icon library, supporting AI coding assistants and proxy applications to access icon resources.

A TypeScript - based MCP server for file system editing tools, ported from the Anthropic computer usage demonstration.

MCP Research Router is an MCP aggregator and intelligent router that can manage multiple MCP servers in a unified manner, provide intelligent tool recommendation and batch parallel execution functions, and improve tool usage efficiency.

The Fortnox MCP Server is a tool for integrating the Swedish accounting system Fortnox. Through the MCP protocol, LLM can manage invoices, customers, suppliers, orders, accounts, and vouchers, and provide business intelligence analysis. It supports both remote and local usage modes.

The MCP Chain of Draft Prompt Tool is a tool that enhances the reasoning ability of LLMs. By converting standard prompts into Chain of Draft or Chain of Thought format, it significantly improves reasoning quality and reduces token usage.

Zulook is a tool that provides read-only access to Zulip conversations. It supports three usage methods: CLI command line, MCP server, and ACP proxy. It retrieves and formats chat messages by parsing Zulip URLs.

Lookerctl is a comprehensive command - line tool for large - scale management and optimization of LookML. It provides functions such as local fast verification, usage analysis, dependency mapping, scientific testing, and AI integration, and supports the MCP server for use by AI agents.

JMComic AI is an AI - enhanced tool for the JMComic comic crawler. It exposes functions such as searching and downloading to local AI clients through the MCP protocol, allowing users to operate comic downloads in natural language and injecting usage skills knowledge to improve the AI's decision - making ability.

An example application demonstrating how to integrate and use the ActionMCP gem in a Ruby on Rails project, including component definition and usage demonstrations.

The OpenAPITools SDK is a multi - AI platform tool management library that provides a unified interface to support the integration and execution of tools for models such as Claude, GPT, and LangChain, and supports both local and API usage modes.

Stata-MCP is a tool that uses large language models (LLM) to assist users in completing Stata regression analysis. It supports multiple languages and platforms and provides a comprehensive guide from installation to advanced usage.

This project demonstrates the security risks of using AI agent tools through extendable-agents, especially the potential leakage of sensitive information caused by tool sharing under the MCP protocol, and provides security usage suggestions.

This project uses an optimized GitHub Actions workflow, designed for open-source projects, minimizing resource usage while maintaining quality. It includes functions such as rapid PR checks, a complete CI/CD pipeline, security scans, and automated releases.

An MCP server implementing the Chain of Draft inference method, significantly reducing token usage while maintaining accuracy

Open Deep Research MCP Server is an AI - driven deep research assistant that conducts iterative deep research by combining search engines, web scraping, and AI technology to generate comprehensive reports. It supports two usage methods: MCP protocol and CLI, and has functions such as reliability assessment, scope control, and automatic generation of follow - up questions.

mcp-nexus is a Multi-Provider Model Context Protocol (MCP) server that integrates the Tavily and Brave Search search APIs, providing a unified tool interface, API key rotation management, a Web management interface, and usage monitoring functions.

TokenScope is a token-aware directory exploration tool for large language models, providing intelligent directory structure analysis, token-aware file content extraction, token usage statistics, and comprehensive report generation functions.

Documentation library for the MCP Python SDK, providing documentation for the Python development toolkit of the Model Context Protocol (MCP), including usage guides and API references for the FastMCP server framework.

An MCP server based on the NVIDIA USDCode API, providing an AI assistant tool for Isaac Sim script writing, USD operations, Python code snippets, and API usage assistance.

Google Sheets MCP Server is a server-side application designed to simplify data management through the Google Sheets API, supporting read and write, real-time updates, and automated operations to enhance the Google Sheets usage experience.

The LicenseSpring MCP server implementation provides complete license management and customer operation functions, including license activation, customer management, usage tracking, etc., supporting multiple subscription levels and authentication methods.

The Tyler Forge™ MCP Server provides instant documentation access to the Tyler Technologies web component library for AI tools, supporting component query, code generation, API verification, and design system usage.