MCP Reasoner is an inference enhancement tool designed for Claude Desktop, providing two search strategies, Beam Search and MCTS, and improving the ability to solve complex problems through experimental algorithms.

A two-stage AI dialogue service that combines DeepSeek inference and Claude generation

EasyMCP is a TypeScript library that simplifies the development of Model Context Protocol (MCP) servers. It provides a concise API and experimental decorator support, automatically handling type inference and template configuration.

The Allora MCP Server is an implementation based on the Model Context Protocol (MCP) that provides the function of obtaining machine learning inference data from the Allora network, enabling AI systems to seamlessly access Allora prediction market data.

An MCP server implementation for Deepseek R1, supporting integration with Claude Desktop and providing powerful language model inference services.

The MCP Agent Tool Adapter project enables modular tool invocation through the MCP protocol, supports two agent frameworks, Google ADK and LangGraph, and provides dynamic inference and tool planning capabilities.

An MCP server implementation for Deepseek R1, supporting the Node.js environment and providing powerful language model inference services.

The Deepseek Thinker MCP Server is an MCP service that provides Deepseek inference content, supporting both the OpenAI API and the local Ollama mode, and can be integrated into AI clients.

mcp - scaffold is a development sandbox for verifying the Model Context Protocol (MCP) server, providing support for local LLMs (such as LLaMA 7B) and cloud inference, including a chat interface and reference architecture.

Groq MCP Server is a service that provides fast model inference through the Model Context Protocol (MCP), supporting various functions such as text generation, voice conversion, image analysis, and batch processing.

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

A FastMCP server implementation based on the Replicate API, focusing on providing resource-based access to AI model inference, especially good at image generation functions.

Auto Causal Inference is a project that uses large language models (LLMs) to automatically perform causal inference. Users only need to specify the treatment variable and the outcome variable, and the system can automatically complete the full - process analysis, including variable role identification, causal graph construction, effect estimation, and model validation. The project provides two agent architectures (LangGraph and MCP) to achieve this function, which is particularly suitable for causal problem analysis in the banking scenario.

This project is an unofficial Clarifai MCP server that acts as a local bridge to connect to the Clarifai API, supporting functions such as image generation, inference, and search, and interacting with the client through the standard MCP protocol.

An intelligent agent system running locally, combining inference models and tool - calling models

A DeepSeek inference service project built by Claude

Enhance Claude's ability to handle complex tasks by integrating the inference engine of DeepSeek R1

AI00 RWKV Server is an efficient inference API server based on the RWKV language model, supporting Vulkan acceleration and OpenAI-compatible interfaces.

Fluent MCP is a modern framework for building Model Context Protocol (MCP) servers with intelligent inference capabilities. It supports AI integration, tool separation, and offloading of complex inferences, and uses a dual - layer LLM architecture for efficient inference.

A local LLM inference MCP server based on Playwright and Web-LLM, realizing text generation, chat interaction, and model management functions through browser automation.

DeepSeek MCP Server enhances Claude's inference capabilities by integrating the advanced inference engine of DeepSeek R1, enabling it to handle complex multi - step inference tasks.

eShopLite is a lightweight .NET-based eCommerce platform that offers features such as semantic search, cloud platform integration, and intelligent inference models to help developers quickly build and scale online stores.

The DeepSeek MCP server enhances Claude's reasoning ability by integrating the advanced inference engine of DeepSeek R1, enabling it to handle complex multi-step reasoning tasks.

The DeepSeek MCP Server enhances Claude's inference capabilities by integrating the advanced inference engine of DeepSeek R1, enabling it to handle complex multi-step inference tasks.

This project enhances Claude's ability to handle complex reasoning tasks by integrating the inference engine of DeepSeek R1 and provides an efficient and accurate multi - step reasoning solution.

The MCP Agent Tool Adapter is a project that implements modular tool invocation through the MCP protocol and supports dynamic inference tools of two agents, Google ADK and LangGraph.

vLLM is an efficient and easy - to - use LLM inference and service library that supports multiple model architectures and optimization techniques, providing high - performance LLM services.

An MCP service that combines the inference capabilities of DeepSeek R1 and the generation capabilities of Claude 3.5

An MCP server implementation that provides inference capabilities of the Gemini language model for Claude Desktop

IntelliGlow is a smart lighting system based on the MCP protocol that controls real smart bulbs through an AI assistant, supports voice commands, AI inference, and direct hardware control, and enables natural language interaction and intelligent lighting management.

mcp-scaffold is a sandbox environment for verifying the Model Context Protocol (MCP) server, supporting local and cloud LLM inference, providing a chat interface and reference architecture.

The DeepSeek-Claude MCP Server enhances Claude's ability to handle complex reasoning tasks by integrating the advanced inference engine of DeepSeek R1.

Sensei MCP is a multi-role engineering tutor system that integrates 64 professional AI roles and provides engineering standards and suggestions through collaborative guidance. It can inject relevant engineering specifications before Claude's inference, supports multiple file types and context awareness, and has session memory and team collaboration functions.