#develop

⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks

Open-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.

Spec Oxide is a comprehensive workflow and toolset that enables spec-driven development for AI-assisted coding with Claude Code. You agree on what to build before any code is written. Spec Oxide ships a CLI and an MCP server to list and manage specifications as Markdown files as well as change proposals. A built-in search functionality finds the relevant spec files to avoid loading too many files into the Claude Code context window.

Persistent memory for AI coding assistants. Works across Cursor, Claude, Windsurf, VS Code and any MCP client. Remember decisions, search semantically, analyze code dependencies — 60+ tools. Your AI's permanent brain.

A growing collection of MCP tools for Android Development. Currently features a deterministic Figma-SVG-to-Android-XML converter, with plans for Gradle analysis, Resource management, and ADB integration tools.

CodeConductor IDE Orchestrator gives Claude Desktop full access to your development environment through a secure MCP server. It connects Claude to your VS Code workspace, enabling real file operations, code navigation, Git workflows, and automated development tasks. The server exposes 24 IDE tools, including: File operations — open, read, write, list, search Code intelligence — go to definition, find references, diagnostics Git automation — status, diff, stage, commit, push (Pro) Command execution — run terminal commands safely (Pro) Command Execution Safety: Pro users can run commands through Claude, but everything is protected by a three-tier safety system. Safe commands run automatically, while higher-risk commands require explicit confirmation and are screened for dangerous patterns. This prevents accidental damage and blocks command injection attempts. All operations run locally on your machine, never transmit code, and follow a tier-based permission system (Free vs Pro). Requires the CodeConductor VS Code extension to function. This orchestrator turns Claude into a capable, controlled development assistant that operates directly inside your real project.

Build, test, debug, and interact with desktop and mobile applications with the Tauri framework. Screenshots, DOM state, and console logs from your running app give the AI rich context to understand what's happening—and tools to interact with it.

Open-source RAG platform to build secure, intelligent AI agents for enterprise data.

The TestingBot MCP server allows you to take screenshots of your website on multiple browsers and operating systems. Create CDP sessions and interface with the TestingBot service.

Stops AI from writing duplicate code. Forces Claude/Cursor/Windsurf to analyze existing code first, get approval on plans, then execute step-by-step. Engineering gates ensure no hallucinations or breaking changes.

The Stack Overflow Model Context Protocol (MCP) enables AI tools and agents to access trusted developer knowledge from Stack Overflow. It standardizes how knowledge is exposed, discovered, and retrieved for use in agent workflows and developer environments.

The MailerSend MCP server lets you connect AI tools directly to your MailerSend account for real-time email management using the most current data. Use natural language prompts to send emails, manage domains, analyze performance, troubleshoot, and more. Quick and easy setup, just connect, authorize and start handling transactional email tasks faster and smarter.

Persistent codebase intelligence that gives agents memory across sessions.

Arch MCP provides three main capabilities: - 🔍 Resources - URI-based access to Arch Wiki, AUR packages, official repos, and installed packages - 🛠️ Tools - Search, analyze, and securely install packages with built-in safety checks - 📋 Prompts - Guided workflows for troubleshooting, security audits, and dependency analysis

Use zip1.io directly from AI assistants like Claude through the Model Context Protocol (MCP). Shorten URLs, retrieve analytics, and manage links using natural language commands.

The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.

The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.

本插件为 Model Context Protocol（MCP）提供了企业级 OpenAPI 文档能力，自动聚合并标准化 企业微信 与 飞书 的开放接口文档的MCP服务。 适用于构建企业内部集成、自动化工作流、Bot/Agent 开发等高频 API 使用场景

本插件为 Model Context Protocol（MCP）提供了企业级 OpenAPI 文档能力，自动聚合并标准化 企业微信 与 飞书 等的开放接口文档。 通过统一上下文调用、搜索和补全，开发者可在无需频繁查阅官网文档的情况下，快速获取接口定义、请求参数、响应结构及权限要求。 适用于构建企业内部集成、自动化工作流、Bot/Agent 开发等高频 API 使用场景。

Smart AI Bridge is a production-ready Model Context Protocol (MCP) server that orchestrates AI-powered development operations across multiple backends with automatic failover, smart routing, and advanced error prevention capabilities. Key Features 🤖 Multi-AI Backend Orchestration Pre-configured 4-Backend System: 1 local model + 3 cloud AI backends (fully customizable - bring your own providers) Fully Expandable: Add unlimited backends via EXTENDING.md guide Intelligent Routing: Automatic backend selection based on task complexity and content analysis Health-Aware Failover: Circuit breakers with automatic fallback chains Bring Your Own Models: Configure any AI provider (local models, cloud APIs, custom endpoints) 🎨 Bring Your Own Backends: The system ships with example configuration using local LM Studio and NVIDIA cloud APIs, but supports ANY AI providers - OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, custom APIs, or local models via Ollama/vLLM/etc. See EXTENDING.md for integration guide. 🎯 Advanced Fuzzy Matching Three-Phase Matching: Exact (<5ms) → Fuzzy (<50ms) → Suggestions (<100ms) Error Prevention: 80% reduction in "text not found" errors Levenshtein Distance: Industry-standard similarity calculation Security Hardened: 9.7/10 security score with DoS protection Cross-Platform: Automatic Windows/Unix line ending handling 🛠️ Comprehensive Toolset 19 Total Tools: 9 core tools + 10 intelligent aliases Code Review: AI-powered analysis with security auditing File Operations: Advanced read, edit, write with atomic transactions Multi-Edit: Batch operations with automatic rollback Validation: Pre-flight checks with fuzzy matching support 🔒 Enterprise Security Security Score: 9.7/10 with comprehensive controls DoS Protection: Complexity limits, iteration caps, timeout enforcement Input Validation: Type checking, structure validation, sanitization Metrics Tracking: Operation monitoring and abuse detection Audit Trail: Complete logging with error sanitization 🏆 Production Ready: 100% test coverage, enterprise-grade reliability, MIT licensed 🚀 Multi-Backend Architecture Flexible 4-backend system pre-configured with 1 local + 3 cloud backends for maximum development efficiency. The architecture is fully expandable - see EXTENDING.md for adding additional backends. 🎯 Pre-configured AI Backends The system comes with 4 specialized backends (fully expandable via EXTENDING.md): Cloud Backend 1 - Coding Specialist (Priority 1) Specialization: Advanced coding, debugging, implementation Optimal For: JavaScript, Python, API development, refactoring, game development Routing: Automatic for coding patterns and task_type: 'coding' Example Providers: OpenAI GPT-4, Anthropic Claude, Qwen via NVIDIA API, Codestral, etc. Cloud Backend 2 - Analysis Specialist (Priority 2) Specialization: Mathematical analysis, research, strategy Features: Advanced reasoning capabilities with thinking process Optimal For: Game balance, statistical analysis, strategic planning Routing: Automatic for analysis patterns and math/research tasks Example Providers: DeepSeek via NVIDIA/custom API, Claude Opus, GPT-4 Advanced, etc. Local Backend - Unlimited Tokens (Priority 3) Specialization: Large context processing, unlimited capacity Optimal For: Processing large files (>50KB), extensive documentation, massive codebases Routing: Automatic for large prompts and unlimited token requirements Example Providers: Any local model via LM Studio, Ollama, vLLM - DeepSeek, Llama, Mistral, Qwen, etc. Cloud Backend 3 - General Purpose (Priority 4) Specialization: General-purpose tasks, additional fallback capacity Optimal For: Diverse tasks, backup routing, multi-modal capabilities Routing: Fallback and general-purpose queries Example Providers: Google Gemini, Azure OpenAI, AWS Bedrock, Anthropic Claude, etc. 🎨 Example Configuration: The default setup uses LM Studio (local) + NVIDIA API (cloud), but you can configure ANY providers. See EXTENDING.md for step-by-step instructions on integrating OpenAI, Anthropic, Azure, AWS, or custom APIs. 🧠 Smart Routing Intelligence Advanced content analysis with empirical learning: // Smart Routing Decision Tree if (prompt.length > 50,000) → Local Backend (unlimited capacity) else if (math/analysis patterns detected) → Cloud Backend 2 (analysis specialist) else if (coding patterns detected) → Cloud Backend 1 (coding specialist) else → Default to Cloud Backend 1 (highest priority) Pattern Recognition: Coding Patterns: function|class|debug|implement|javascript|python|api|optimize Math/Analysis Patterns: analyze|calculate|statistics|balance|metrics|research|strategy Large Context: File size >100KB or prompt length >50,000 characters

Enables AI tools to interact with ConfigCat, a feature flag service for teams. Supports managing ConfigCat feature flags, configs, environments, products and organizations. Helps to integrate ConfigCat SDK, implement feature flags and remove zombie (stale) flags.

Magic-API MCP Server - A Model Context Protocol server for Magic-API development

Create and manage feature flags. Enable your editor to understand your feature flags, their states, and their relationships within your codebase.

Transform your AI agents into Apple development experts! Apple RAG MCP gives you instant access to official Swift docs, design guidelines, and comprehensive Apple platform knowledge through cutting-edge RAG technology. With professional AI reranking and hybrid search across iOS, macOS, watchOS, tvOS, and visionOS documentation plus Apple Developer YouTube content, you'll get precise, contextual answers every time. Compatible with Cursor, Claude Desktop, and all MCP tools - start building smarter Apple apps today!

Webvizio MCP Server - Automatically converts feedback and bug reports from websites and web apps into actionable, context-enriched developer tasks. Delivered straight to your AI coding tools, the Webvizio MCP Server ensures your AI agent has all the data it needs to solve tasks with speed and accuracy.

Collègue est un serveur MCP d’assistance au développement, basé sur FastMCP, qui automatise l’analyse, la génération, le refactoring, la documentation et la création de tests unitaires pour du code multi‑langages, avec configuration LLM dynamique et intégration OAuth/Keycloak.

Provide docs and source code access for the HMR library on PyPI. Docs: https://py3.online/hmr

Smart, case-aware search & replace for codebases. Provides atomic renaming of symbols, files, and directories with full undo/redo. The MCP server lets AI assistants plan, preview, and apply rename operations safely, handling all naming conventions (snake_case, camelCase, PascalCase, etc.) automatically.

MCP server for Roll Docker Stack and multi-framework development environments.

Provides context optimization tools to extract targeted information rather than processing large files and command outputs in their entirety.

An MCP (Model Context Protocol) server for controlling and interacting with Xcode from AI assistants and LLMs like Claude Code, Cursor, Claude Desktop, LM Studio, etc. This server significantly improves the build cycle. Now Claude (or your favorite tool) can directly command Xcode to build your project. Because Xcode is building it directly (rather than xcodebuild command-line or similar), the build happens exactly the same way as when you build it in Xcode. Xcode-mcp-server returns relevant build errors or warnings back to your coding tool (like Cursor or Claude Code), so the LLM sees exactly the same errors you do. Included tool functions here - you don't really need to know this info because your coding LLM will get this info (and more details) automatically, but I've included it here for the curious: - version - Returns xcode-mcp-server's version string - get_xcode_projects - Finds all .xcodeproj and .xcworkspace projects in the given search_path. If search_path is empty, all paths to which the tool has been granted access are searched - get_project_hierarchy - Returns the path hierarchy of the project or workspace - get_project_schemes - Returns a list of build schemes for the specified project - build_project - Commands Xcode to build. This is the workhorse that builds your project again and again, returning success or build errors - run_project - Commands Xcode to run your project - get_build_errors - Returns most recent build errors from the given project - clean_project - Cleans build

Trigger a help request directly from your IDE via MCP and get human help in minutes

Spring AI Playground is a self-hosted web UI that simplifies AI experimentation and testing. It provides Java developers with an intuitive interface for working with large language models (LLMs), vector databases, prompt engineering, and Model Context Protocol (MCP) integrations. Built on Spring AI, it supports leading model providers and includes comprehensive tools for testing retrieval-augmented generation (RAG) workflows and MCP integrations. The goal is to make AI more accessible to developers, helping them quickly prototype Spring AI-based applications with enhanced contextual awareness and external tool capabilities.

An AI-powered development workflow MCP server that guides you from requirements to code implementation. Features Complete Development Workflow: From goal collection to task execution AI-Powered Guidance: Step-by-step instructions for each development phase Template-Based: Uses proven templates for requirements, design, and tasks Claude Integration: Seamlessly integrates with Claude Code Installation

A Model Context Protocol (MCP) server for YouTube video transcripts and search.

Enables AI agents to compile code and run tests in Unity Editor.

An AI-powered developer experience for Aptos that lets users vibe code and deploy full-stack dApps with minimal setup.

Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.

A comprehensive JSON Schema validation server implementing the Model Context Protocol (MCP) with support for JSON Schema Draft 2020-12, external references, schema management, and real-time streaming validation.

Deepgram Saga is the first voice-native MCP client built for developers. It lets you speak natural commands to trigger actions across tools like GitHub, Linear, Slack, and Notion – no context switching required. Saga runs as a desktop app and supports any MCP server, turning fuzzy ideas into structured prompts, code, and commits. It’s optimized for end-to-end dev workflows, from scaffolding features to logging issues and sending updates. Voice in, work out.

A simple MCP server that lets your AI agent see and capture the web.

HAP (Super Application Platform) is developed by Mingdao（ https://www.mingdao.com ）The launched APaaS platform helps you build enterprise level applications quickly without coding. This is HAP's MCP (Model Context Protocol) server, used for seamless integration of AI. It enables every zero code application built through HAP to quickly become a tool for agents.

Warp is the fastest way to build with multiple AI agents—from writing code to shipping it. The best overall coding and terminal agent.

Streamline development server management for AI coding agents. SupervisordMCP combines Circus process manager with Model Context Protocol (MCP), eliminating shell command complexity and reducing token consumption for AI-driven development workflows.

QuerySculptor is a GraphQL query builder designed for AI agents that provides 26 structured tools via the Model Context Protocol (MCP). Instead of generating complex GraphQL queries from scratch, AI agents can build queries step-by-step with real-time validation, schema introspection, and error prevention. It works with Claude, Cursor, and other MCP clients, using Redis for session management and featuring a live demo with the Pokemon API. The tool transforms the traditional error-prone approach of raw GraphQL generation into a guided, conversational workflow perfect for AI assistants and chatbots.

Streamline development server management for AI coding agents. CircusMCP combines Circus process manager with Model Context Protocol (MCP), eliminating shell command complexity and reducing token consumption for AI-driven development workflows.

The 4EVERLAND Hosting MCP Server enables users to leverage AI-driven workflows to deploy code instantly to decentralized storage networks such as Greenfield, IPFS, and Arweave. Upon deployment, it provides a directly accessible webpage domain, streamlining the process of deploying and sharing decentralized applications.

协助AI开发者需求完善、模块设计、技术架构设计的mcp

Tool to fetch and summarize developer documentation from [MDN Web Docs](https://developer.mozilla.org/). ## Features - Search MDN for documentation using a query string. - Returns a summary (first paragraph) and a link to the full documentation. - Exposes an MCP-compatible tool server over stdio.

MCP server for session continuity and sandbox safety in LLM development workflows. Provides "pick up exactly where you left off" + "never break the main app" functionality.

For MCP Server Development

This repository provides a tool for converting SVG files into various font formats, streamlining icon management. With features like automatic CSS generation and TypeScript support, it simplifies the process for developers. 🐙🌟

Trying things realted to MCP server

Interop CLI: Go command-line tool for efficient project management and command execution across your development workspace.

🧪 Official MCP Server for Debugg AI AI-driven browser automation and E2E test server implementing the Model Context Protocol (MCP), designed to help AI agents test UI changes, simulate user behavior, and analyze visual outputs of running web applications — all via natural language and CLI tools.

Complete development environment setup for Claude Code with MCP servers, dev containers, and long-running job capabilities

how to develop mcp server and debugging from local to azure

A Model Context Protocol (MCP) server providing tools for NPM package management and dependency updates. Helps LLMs like Claude interact with npm packages, search npm registry, and keep dependencies up-to-date.

🎨 MCP Server that converts SVG icons into web fonts with CSS and TypeScript support. Generate icon fonts from directories of SVG files.

This is a collection of example MCP Servers for development.

提供对 [public-apis](https://github.com/public-apis/public-apis) 数据库的智能访问和管理功能。为开发者提供便捷的公共 API 发现、搜索和集成服务。通过标准化的 MCP 协议，您可以轻松地在各种 AI 助手和开发工具中集成丰富的公共 API 资源。

MCP server code for context-mcp

A comprehensive NixOS Flake development environment for the Playwright MCP (Model Context Protocol) server with full Chrome and Firefox support, including persistent browser profiles.

Stop AI coding disasters before they cost you weeks. Real-time anti-pattern detection for vibe coders who love AI tools but need a safety net to avoid expensive overengineering traps.

A Model Context Protocol server that provides task orchestration capabilities for AI assistants

AWS MCP Servers — specialized MCP servers that bring AWS best practices directly to your development workflow

An MCP server that provides filesystem access to Claude desktop

Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration in development environments.

Model Context Protocol server for Rust development tools (clippy, rustfmt, cargo check, cargo test)

MCP server and a unified TUI for managing dev servers + Playwright

This is the official repo for the Harness MCP server

A Model Context Protocol (MCP) compliant server designed for comprehensive web research. It uses Tavily's Search and Crawl APIs to gather detailed information on a given topic, then structures this data in a format perfect for LLMs to create high-quality markdown documents.

A Model Context Protocol (MCP) server providing tools for NPM package management and dependency updates. Helps LLMs like Claude interact with npm packages, search npm registry, and keep dependencies up-to-date.

The npm-package-mcp-server allows users to efficiently access and analyze source code from any NPM package. With features like smart file discovery and selective code reading, it streamlines the process for developers. 🐙🌐

Port is a developer portal-native AI that offers AI agents and an MCP server to build software catalogs, enable self-service actions, and connect directly to your IDE for smooth workflows.

This project provides an MCP-compatible interface for the JSONBuddy Core API, enabling JSON validation against schemas via a secure HTTP-based service. The server exposes two endpoints (`/validator/validate` and `/validator/validate-simple`) for flexible schema validation scenarios. MCP clients and AI agents can integrate this API using the included `mcp.json` definition and standard API key authentication.

A Sui blockchain MCP service for development

A Model Context Protocol (MCP) server providing tools for NPM package management and dependency updates. Helps LLMs like Claude interact with npm packages, search npm registry, and keep dependencies up-to-date.

GitHub MCP server test repository

MCP server and AI agents

Centralized management of AI tool configurations (rules, commands, MCP servers) with streamlined setup for global and project-specific environments.

CodeCompass: AI-powered Vibe Coding with MCP. Connects Git repositories to AI assistants like Claude, using Ollama for privacy or OpenAI for cloud. Integrates with VSCode, Cursor, and more.

A repository for practicing MCP Server develop

Cursor AI SSOT & Rule Engine Template: A comprehensive framework for integrating Cursor AI's advanced features into any project. Includes Single Source of Truth (SSOT) tracking, custom project rules, and Model Context Protocol (MCP) with Knowledge Graph for intelligent context management.

Repository for MCP Server development

A MCP Server of

This project provides sample MCP servers that can be used with Amazon Q CLI or other MCP-compatible AI assistants

Docker Container with Useful MCP Servers

A platform for managing your local MCP servers

This MCP server allows AI to use a number of functions from the Liveblocks REST API. For example, it can create, modify, and delete different aspects of Liveblocks such as rooms, threads, comments, notifications, and more. It also has read access to Storage and Yjs.

Quickstart mcp for server developer

Zero setup to use Code Runner MCP Server in VS Code for running code snippet and show the result.

Production-ready Model Context Protocol (MCP) servers in Python, Go, and Rust for VS Code integration. Enables AI systems to interact with tools via standardized interfaces.

MCP server for Payload CMS 3.0, designed to help developers validate code, generate templates, and scaffold projects following best practices.

ACI.dev is the open source platform that connects your AI agents to 600+ tool integrations with multi-tenant auth, granular permissions, and access through direct function calling or a unified MCP server.

Website Generator enables AI to create complete, editable websites from simple prompts, returning links to view and customize the site without requiring technical expertise.

ARC Model Context Protocol (MCP) Server: AI-Powered Development using the ARC framework.