WebMCP is a project that allows websites to support client-side LLMs (Large Language Models). It enables the sharing of tools, resources, and prompts between websites and LLMs through a local WebSocket server without the need for API keys and supports multiple models.

This project is a deep research server based on the Ollama local large - model, providing automated research tools through the MCP protocol, capable of iterative search, analysis, and summarization of complex topics.

An MCP server tool that connects Claude with large language models running in local LM Studio

The Ollama MCP Server is a bridge tool that connects the local large language models of Ollama and the Model Context Protocol (MCP). It provides complete API integration, model management, and execution functions, and supports OpenAI - compatible chat interfaces and visual multimodal models.

File Context MCP is a TypeScript-based application that provides an API to query large language models (LLMs) through local file content. It supports multiple LLM providers (Ollama and Together.ai) and can process multiple file types to generate context-aware responses.

The Local MCP Tools Collection aims to simplify the integration of multi - functional tools for local large language models, supporting multiple MCP servers through a single virtual environment, including web search, Python sandbox, and long - term memory functions.

FastApply MCP Server is an enterprise-level code intelligence platform that provides comprehensive code analysis, search, and refactoring capabilities through local AI models, AST semantic search, security scanning, and intelligent pattern recognition. It supports multi-language development and large codebase processing.

MCP Tools is a server project that implements the Model Context Protocol (MCP), providing file system and command execution tools for LLM clients such as Claude Desktop, and extending the local system interaction capabilities of large language models.

Agent Farm v3.4 is a system based on AI agent evolution and parallel task execution, which realizes task processing through tool - enhanced agents. The new version introduces the chunked write mode, supports the parallel generation of large documents and code files, improves performance by 8.6 times, and uses local models for result synthesis without relying on cloud tokens.

An MCP server that does not require local deployment, specifically designed for handling mathematical calculations. It can provide permanently accurate mathematical calculation capabilities for large language models through simple configuration.

An MCP server that combines Claude Code and Google Gemini AI to achieve in - depth code analysis through multi - model collaboration. Claude is good at local context operations and CLI workflows, while Gemini uses its ultra - large context window for distributed system debugging and long - trace analysis.

Checkstyle MCP Server is a middleware that connects large language models with local code quality tools, supporting code checking and formatting for languages such as Go, Java, and Lua, and providing project configuration management and AI self - correction functions.

Claude-LMStudio-Bridge is an MCP server that connects Claude with large language models running locally through LM Studio, supporting two-way communication and model comparison.

The RLM MCP Server is a large-scale context processing tool based on the Recursive Language Model pattern. It allows Claude Code to process text of over 10 million tokens through external variables, avoiding directly inputting massive content into the prompt. Through the processes of loading, chunking, sub-querying, and aggregation, it supports automatic analysis and programmatic execution, and can connect to the Claude API or the local Ollama for free inference.

The Unity MCP and Ollama integration package enables seamless communication between Unity and local large language models, supporting asset management and editor automation.

Tome is a MacOS application (support for Windows and Linux is coming soon) developed by the Runebook team. It aims to simplify the use of local large language models (LLMs) with MCP servers. By integrating Ollama and managing MCP servers, users can quickly start chatting with MCP-powered models without dealing with complex configurations.

The 302AI Basic MCP Server is a toolkit that enhances the basic capabilities of large language models. It supports dynamically loading a list of remote tools, provides multiple usage modes (local stdin or remote HTTP service), and includes practical tools such as Wiki search, Arxiv search, calculator, and code execution.

Ollama-MCP-server is a middleware server that connects the local Ollama large language model. It provides task decomposition, result evaluation, and model management functions through the Model Context Protocol, supporting standardized communication and performance optimization.

repo-to-txt-mcp is a server based on the MCP protocol that converts GitHub repositories or local folders into structured text files, facilitating the provision of context information for large language models. It supports file filtering, token management, and can be integrated with the Cursor editor.

XiYan MCP Server is a model context protocol server based on XiYan - SQL. It supports querying databases through natural language and provides multiple model configuration options, including general large models, SOTA text - to - SQL models, and local models. It is suitable for scenarios with different security and performance requirements.

A knowledge graph builder that uses a local AI model to convert text or web page content into structured knowledge graphs, supporting large-scale content processing, real-time visualization, and integration with Neo4j and Qdrant databases.

A RAG system built with open-source embedding models, vector databases, and the Gemini large language model, supporting local document processing and dynamic index update.

This project is an MCP server designed to help large language models (LLMs) accurately obtain Quranic text through the Quran API and avoid generating incorrect content. It provides an integration solution with the Claude desktop application and enables accurate Quranic verse queries through a local server.

A multilingual localization translation tool based on large language models, supporting intelligent processing and batch translation of multiple file formats

An MCP server based on the recursive language model pattern, which processes ultra - large - scale contexts (over 10 million tokens) through chunking, sub - queries, and local inference, supporting automatic analysis, code execution, and security filtering.

interactive-mcp is an MCP server implemented based on Node.js/TypeScript, aiming to promote local interaction between large language models (LLMs) and users, providing functions such as user input requests, system notifications, and command-line chat sessions.

Basic Memory is a tool for building persistent knowledge through natural conversations with large language models (LLMs). It stores data locally in Markdown files and implements the MCP protocol for two - way knowledge management.

Unity MCP is a bridge tool that connects the Unity editor and large language models (LLMs). It enables natural language control of the Unity editor through the local MCP client, supporting automated operations such as asset management, scene control, and script editing.