Wren Engine is a semantic engine designed for MCP clients and AI agents, providing semantic layer support to enable AI to accurately understand enterprise data models and business logic. It supports multiple data sources and is embedded in MCP clients to ensure the accuracy and governance of data interaction.

MCPBench is a framework for evaluating the performance of MCP servers. It supports the evaluation of two types of tasks: web search and database query, is compatible with local and remote servers, and mainly evaluates accuracy, latency, and token consumption.

HyperTool is an MCP server management tool that allows the AI to dynamically switch and use toolsets from multiple MCP servers, breaking the tool quantity limit and improving the accuracy and efficiency of AI tool selection through intelligent toolsets.

An MCP server built on Deno and TypeScript, providing context information related to Terragrunt documentation and GitHub issues, aiming to improve IDE support and AI assistance accuracy when writing IaC configurations.

A text editor server built on Python and FastMCP, providing powerful file operation tools. It enables file reading, editing, and management through a standardized API, and specifically optimizes the accuracy and reliability of code editing by AI assistants.

The VibeCheck Web testing tool is an AI-driven web testing agent integrated into AI programming assistants (such as GitHub Copilot, Cursor, etc.) through the MCP protocol to achieve automated test recording, execution, and discovery. It uses Playwright to control the browser, supports generating test scripts through natural language description, executes regression tests, and automatically discovers potential test steps, improving development efficiency and test accuracy.

An MCP server based on Deno and TypeScript that provides context information query functions for Terragrunt documentation and GitHub issues, aiming to improve the Terragrunt development experience and the accuracy of AI-assisted tools.

Cortex MCP is a model context protocol server that provides access to the Cortex API and uses workspace-related context to enhance the accuracy of question answers.

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

This is a fashion recommendation system based on CLIP. It detects the clothing pictures uploaded by users through YOLO and recommends similar products after encoding with CLIP. The project has completed the construction of the FastAPI server, database connection, and basic front - end UI. The next step is to optimize the label accuracy of CLIP and system integration.

The Model Context Protocol (MCP) is an open - source protocol released by Anthropic, aiming to solve the standardization problem of connecting large language models (LLMs) with external data sources and systems. It provides a structured framework that enables models to integrate and utilize external context, thereby expanding their capabilities and improving response accuracy. MCP supports functions such as knowledge expansion, external tool calls, and pre - written prompts.

A server based on the Model Context Protocol (MCP) that provides access to clinical guidelines from the National Comprehensive Cancer Network (NCCN). This system ensures the accuracy and reliability of medical guidance by directly reading the PDF content of the guidelines instead of using RAG technology.

The MCP Code Indexer is an intelligent code retrieval tool designed specifically for large AI language models. It improves the efficiency and accuracy of code processing through semantic understanding and vectorized indexing, supporting functions such as code analysis, quality assessment, and dependency management.

The MCP Wolfram Alpha Server is a Go-based MCP server that provides high-precision calculation support for LLMs by integrating the Wolfram Alpha API, addressing the limitations of LLMs in numerical calculations and improving calculation accuracy and efficiency.

Linkup for Claude is a tool that provides real-time internet access and high-quality content search capabilities for the AI assistant Claude, breaking through its knowledge cut-off limit and enhancing the timeliness and accuracy of its responses.

The Eka MCP Server is a medical knowledge base interaction service developed by Eka Care, focusing on the Indian medical scenario. It provides a structured query function for drug brands and treatment plans to improve the accuracy and reliability of AI medical responses.

The MCP Domain Availability Checker is a tool integrated with Claude Desktop that provides domain availability checking across multiple top-level domains, supports over 50 popular TLD extensions, and combines DNS and WHOIS dual verification to ensure accuracy.

Linkup for Claude is a tool that provides real-time Internet access capabilities for the AI assistant Claude, breaks through its knowledge cutoff limit, enables it to obtain the latest news, high-quality content, and trusted sources, and improves the timeliness and accuracy of answers.

ProjectDocHelper is an MCP server tool used to automatically generate project documents and integrate them with AI development tools through the MCP protocol, improving the accuracy and relevance of AI responses.

The Framelink Figma MCP server provides access to Figma design data for AI programming tools and simplifies the API response to improve the accuracy of AI in implementing designs.

Linkup for Claude is a plugin that provides real-time Internet access capabilities for the AI assistant Claude, breaking through the limit of its knowledge cutoff date, enabling it to obtain the latest news and high-quality content, and improving the accuracy and timeliness of answers.

The RevenueBase MCP Server provides access to the industry-leading email verification API, supporting functions such as real-time verification, batch processing, and credit management, with an accuracy rate of over 99%.

An MCP service that efficiently extracts JSON data from URLs using JSONPath, significantly reducing the number of tokens processed by the LLM and improving data accuracy

This project provides an interface for AI assistants to access Haskell documentation. By retrieving authoritative documentation on Hackage in real - time, it solves the problem of insufficient training data for AI in the Haskell field and improves the accuracy of code generation and explanation.

A small tool that improves the accuracy of WeChat QR code recognition through two-stage detection. First, use YOLOv8 to locate the position of the QR code, and then use the WeChat open-source model to extract the content.