Serena is a powerful open - source coding agent toolkit that can transform LLMs into full - fledged agents that can work directly on codebases. It provides IDE - like semantic code retrieval and editing tools, supports multiple programming languages, and can be integrated with multiple LLMs via the MCP protocol or the Agno framework.

Refact Agent is an open - source AI programming assistant that supports multi - language code generation, debugging, and optimization. It integrates with mainstream development tools, can be deployed locally, and provides intelligent code completion and code explanation functions.

This is a curated list of Web3 Model Context Protocol (MCP) servers, covering multiple categories such as chain interaction, trading, DeFi, market data, tools, and social. MCP is an open protocol that standardizes how applications provide context to LLMs, similar to the USB - C port for AI applications. DeMCP is the first decentralized MCP network, focusing on providing self - developed and open - source MCP services for agents, supporting cryptocurrency payments, and redefining the security and reliability of MCP by combining TEE and blockchain registries.

MCPAdapt is an open - source project aiming to seamlessly integrate the tools of over 650 MCP servers into various agent frameworks, enabling developers to easily use these tools in their agent workflows.

ACI.dev is an open-source AI agent tool infrastructure that provides multi-tenant authentication, permission management, and dynamic discovery functions for over 600 pre-integrated tools. It supports calls through a unified MCP Server or a lightweight SDK, simplifying the development of production-level AI agents.

This project demonstrates an SSE-based implementation mode of the MCP server and client, allowing agents (clients) to connect and use the tools provided by the server at any time, suitable for cloud-native scenarios.

This is an AI development tool project based on Docker containers. It uses Markdown files to write complex workflows, combines Dockerized tools with the LLM model selected by the user, and implements a workflow of multi - model agents and project - priority design.

adb - mcp is a proof - of - concept project aiming to provide an interface for LLMs through the MCP protocol to create an AI agent for controlling Adobe tools (such as Photoshop and Premiere). This project includes the MCP server, Node command proxy server, and Adobe application plugins, supporting natural language instruction operations on Adobe software and suitable for image and video editing automation.

The Dify MCP client plugin, as an agent strategy plugin, allows ReAct agent nodes to connect to the MCP server, converting the list of tools, resources, and prompts into Dify tools for LLM to call.

This project demonstrates a real-time multi-tool agent architecture based on LangGraph and the MCP protocol. By decoupling agent orchestration and tool execution, it realizes a modular and scalable AI system. The MCP service supports multiple transport protocols (SSE/STDIO), allows AI agents to dynamically call remote tools, and has cross-language and cloud deployment capabilities.

Canvas MCP is a set of tools that enables AI agents to interact with Canvas LMS and Gradescope, providing functions such as course resource query and assignment management.

Speelka Agent is a general LLM agent based on the Model Context Protocol (MCP), capable of invoking tools from other MCP servers to achieve complex task decomposition, multi - model collaboration, and tool orchestration.

Cursor Rust Tools is an MCP server that provides access to Rust Analyzer, Crate documentation, and Cargo commands for the LLM in Cursor, improving the efficiency of AI agents in Rust development.

This project is an MCP client based on LangChain, used to demonstrate how to call MCP server tools through the LangChain ReAct Agent. It supports the LLMs of Anthropic, OpenAI, and Groq and provides the function of converting MCP tools to LangChain tools.

This project creates an AI agent based on the n8n platform that can discover and use Model Context Protocol (MCP) server tools through the Nostr network. The agent searches for available tools by querying Data Vending Machines (DVM) in the network, sends requests, and obtains responses, thereby expanding the functionality of the LLM to use MCP tools that are not installed.

The FHIR MCP Server is a medical data management server based on the FastMCP framework, providing a complete implementation of the Model Context Protocol (MCP) and supporting the interaction between LLM agents and FHIR-compatible backends. It provides standardized interfaces, supports comprehensive CRUD operations on FHIR resources, and implements intelligent document processing and semantic search through a series of tools.

The CodeSandbox MCP server exposes CodeSandbox SDK operations through tools for AI agents to perform operations such as sandbox creation and file read and write.

Binance Alpha MCP is a server for tracking Binance Alpha trades, helping AI agents optimize Alpha point accumulation. It provides real-time trading monitoring, USD-denominated metrics, data persistence, and MCP tools, including functions to get top tokens and trading statistics.

AIM Guard MCP is an AI security protection server that provides security analysis, content detection, and protection instruction tools for AI agents to protect the security of MCP interactions.

Octagon MCP is a model context protocol server that integrates the Octagon market intelligence API, providing AI - agent analysis tools for public and private market data.

AutoSpectra is an all-in-one AI agent automation platform that provides an integrated solution for browser automation, API testing, debugging tools, etc., and is compatible with multiple AI model systems.

The MCP server implementation of Foxit PDF API, providing Python and TypeScript versions, exposes more than 35 operations (such as creation, conversion, editing, security, OCR, etc.) of Foxit PDF services as tools available to AI agents.

This is a production-level medical agent server template based on the AOP protocol. It can deploy multiple professional medical agents as MCP tools, supporting the discovery and invocation of various medical analysis agents (such as laboratory data interpretation, ICD-10 coding, treatment plans, drug interactions, imaging triage, and clinical note summarization) through MCP clients, and providing functions such as queue management, dynamic discovery, and batch processing.

The Pega DX MCP Server is an experimental project aiming to transform Pega Infinity™ applications into an intuitive conversational experience through the Model Context Protocol (MCP). It serves as a bridge between the Pega DX API and the natural language interface, enabling GenAI agents, IDEs, and other MCP-supported tools to interact with Pega Infinity™ applications using simple human-readable commands.

MCPez is a microservice command proxy management platform that unifies the management and standardizes the interfaces of backend services through a web interface, simplifying the integration of AI agents and tools.

This project implements an MCP server and client for building intelligent agent applications based on Retrieval Augmented Generation (RAG). The server provides tools such as entity extraction, query optimization, and relevance checking, and the client demonstrates how to connect to the server and use these tools to enhance the performance of the RAG system.

click-mcp is a Python library that extends Click applications through Model Context Protocol (MCP) support, enabling AI agents to interact with CLI tools.

MCP Architect is a service that provides comprehensive architecture expertise, supporting multiple architecture fields through professional agents, resources, and tools.

A service implementing the Model Context Protocol (MCP), providing tools for retrieving and analyzing the entire codebase, and supporting AI agents such as Cursor's Composer Agent to automatically read and understand the entire codebase.

Ref MCP is a Model Context Protocol server that provides AI programming tools or agents with access to documentation for APIs, services, libraries, etc. It is a one-stop solution to keep agents updated on documentation in a fast and token-efficient manner.

Codebase MCP is a service that implements the Model Context Protocol (MCP), providing tools for retrieving and analyzing entire codebases through RepoMix, and supporting AI agents such as Cursor's Composer Agent to automatically read and understand large codebases.

A comprehensive real estate data management MCP server, providing tools and resources for property listings, agent management, market analysis, customer relations, and regional intelligence.

The PubMed MCP Server is an interface service based on the Model Context Protocol, providing comprehensive access to the PubMed biomedical literature database for AI agents and research tools. It supports functions such as literature search, metadata acquisition, citation analysis, research plan generation, and data visualization, and is efficiently integrated through the NCBI E - utilities API.

TG_MCP is a lightweight Python interface that exposes TigerGraph operations (queries, schemas, vertices, edges, UDFs, etc.) as structured tools and URI - based resources for MCP agents to use.

GooseTeam is an AI agent collaboration platform that enables task allocation and message management among agents through the MCP protocol. It supports both natural language and flowchart protocol expressions and provides an extended toolset.

The Osmosis Agent Toolkit is a collection of development tools for interacting with the Osmosis protocol, including core functions, AI SDK integration, and MCP server implementation.

The Letta MCP Server is a server toolset that provides agent management, memory operations, and Letta system integration.

KOI-MCP is a bridge framework that integrates the Knowledge Organization Infrastructure (KOI) with the Model Context Protocol (MCP), enabling autonomous agents to exchange rich personality traits and expose capabilities as standardized tools.

Kubernetes toolset that provides a set of Kubernetes functions for agents to use, supporting direct passing to agents or use through an MCP server. Focuses on monitoring and root cause analysis use cases, providing strongly typed and well-documented tools.

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.