io.github.IamNishant51/atlas-pipeline
编码与调试by iamnishant51
提供 7 阶段 AI pipeline 的 MCP server:从 Intent、Context、Git 到分解、变体、批评与优化。
什么是 io.github.IamNishant51/atlas-pipeline?
提供 7 阶段 AI pipeline 的 MCP server:从 Intent、Context、Git 到分解、变体、批评与优化。
README
Atlas MCP Server
<div align="center">Enterprise-Grade Agentic AI Pipeline for Modern IDEs
Advanced AI/ML-powered development tools with RAG search, ML bug prediction, intelligent code migration, and comprehensive test generation.
Installation • Features • Tools • Usage • Documentation
</div>Overview
Atlas MCP Server transforms your IDE with intelligent development capabilities through a comprehensive analysis pipeline:
Intent → Context → Decomposition → Variants → Critique → Optimization
Natively integrated with Cursor, Windsurf, Claude Desktop, GitHub Copilot, and VS Code.
What's New in Latest Version
Advanced Development Tools Suite
The latest version introduces six powerful tools designed to address complex development challenges:
New Advanced Analysis Tools:
<table> <tr> <td width="30%"><b>Bug Oracle</b></td> <td>Predictive bug detection system analyzing code patterns, complexity metrics, and historical data to forecast potential issues before they occur</td> </tr> <tr> <td><b>Code Whisperer</b></td> <td>Intelligent code suggestion engine providing context-aware recommendations, pattern detection, and best practice enforcement</td> </tr> <tr> <td><b>Codebase Surgeon</b></td> <td>Precision refactoring tool for large-scale codebase transformations with dependency-aware modifications and impact analysis</td> </tr> </table>Enhanced Development Experience:
<table> <tr> <td width="30%"><b>Semantic Search</b></td> <td>Advanced code search with natural language understanding, finding code by intent rather than keywords</td> </tr> <tr> <td><b>Smart Merge Resolver</b></td> <td>Intelligent conflict resolution for git merges using code analysis and context understanding to suggest optimal merge strategies</td> </tr> <tr> <td><b>Tech Debt Quantifier</b></td> <td>Technical debt measurement and tracking system with actionable metrics and prioritized remediation roadmaps</td> </tr> </table>Frontend Developer Tools
Comprehensive suite for modern frontend development:
<table> <tr> <td width="30%"><b>Performance Doctor</b></td> <td>Detects React/Vue re-render issues, bundle bloat, memory leaks, and provides specific code fixes with improvement estimates</td> </tr> <tr> <td><b>CSS Wizard</b></td> <td>CSS architecture analyzer - detects specificity conflicts, generates design tokens, converts between BEM/Tailwind/CSS Modules/styled-components</td> </tr> <tr> <td><b>Animation Studio</b></td> <td>Professional animation generator - CSS keyframes, Framer Motion, GSAP timelines, micro-interactions with accessibility support</td> </tr> <tr> <td><b>API Helper</b></td> <td>API integration assistant - generates TypeScript types, React Query/SWR hooks, mock data, Zod schemas, and error handling</td> </tr> </table>Senior Developer Tools
Expert-level guidance and analysis:
<table> <tr> <td width="30%"><b>Senior Mentor</b></td> <td>Architectural guidance from a 15+ year veteran perspective with trade-off analysis and senior lessons</td> </tr> <tr> <td><b>Performance Optimizer</b></td> <td>Deep performance analysis with Web Vitals optimization and bottleneck detection</td> </tr> <tr> <td><b>Security Scanner</b></td> <td>Enterprise-grade vulnerability detection with compliance assessment (GDPR, CCPA, HIPAA, PCI-DSS)</td> </tr> <tr> <td><b>State Management Architect</b></td> <td>Pattern comparison and scalability analysis for Redux, Zustand, Jotai, Recoil, and more</td> </tr> <tr> <td><b>API Design Consultant</b></td> <td>RESTful and GraphQL API design review with best practices and documentation templates</td> </tr> </table>AI/ML Powered Tools
Advanced machine learning capabilities:
<table> <tr> <td width="30%"><b>RAG Search</b></td> <td>Semantic code search with knowledge graphs and natural language queries</td> </tr> <tr> <td><b>ML Predictor</b></td> <td>Bug & performance prediction with 70-85% accuracy using machine learning</td> </tr> <tr> <td><b>Code Migration</b></td> <td>Intelligent migration (12 types: JS→TS, React upgrades, Callbacks→Async)</td> </tr> <tr> <td><b>Test Generator</b></td> <td>Advanced test generation with edge cases, mocks, and property-based testing</td> </tr> </table>Core Professional Tools
Essential development utilities:
<table> <tr> <td width="30%"><b>Refactor</b></td> <td>Code refactoring engine with complexity analysis</td> </tr> <tr> <td><b>Profiler</b></td> <td>Performance profiling & bottleneck detection (O(n), O(n²), etc.)</td> </tr> <tr> <td><b>Review</b></td> <td>Automated code review with quality scores and security checks</td> </tr> <tr> <td><b>Dependencies</b></td> <td>Dependency analysis, unused package detection, vulnerability scanning</td> </tr> <tr> <td><b>Dashboard</b></td> <td>Interactive HTML metrics dashboards with real-time data</td> </tr> <tr> <td><b>Security</b></td> <td>Security vulnerability scanning (CWE, OWASP standards)</td> </tr> <tr> <td><b>Test Gen</b></td> <td>Comprehensive test case generation (Jest, Vitest, Pytest, Mocha)</td> </tr> <tr> <td><b>Docs Gen</b></td> <td>Auto-generate documentation (JSDoc, TSDoc, PyDoc)</td> </tr> </table>Key Features
<table> <tr> <td width="50%" valign="top">AI/ML Capabilities
- RAG Search - Semantic code understanding with knowledge graphs
- ML Prediction - Bug & performance forecasting (70-85% accuracy)
- Code Migration - 12 intelligent migration types
- Test Generation - Advanced test suites with edge cases
- Bug Oracle - Predictive bug detection and prevention
- Semantic Search - Natural language code discovery
Professional Tools
- Full Pipeline - Intent → Context → Variants → Optimize
- Quality Analysis - Code review, security, complexity
- Performance - Profiling, bottleneck detection
- Automation - Tests, docs, refactoring
- Tech Debt - Quantification and tracking
- Merge Resolution - Intelligent conflict handling
Why Choose Atlas?
- Zero Configuration: No API keys required - leverages your IDE's built-in AI (Copilot/Cursor)
- 33 Professional Tools: Comprehensive suite covering all development needs
- Agentic Workflow: DAG-based task decomposition for complex problems
- Context Aware: Deep project structure, dependencies, and git history analysis
- High Performance: LRU caching, request deduplication, parallel execution
- Enterprise Ready: Production-grade tools with security and compliance features
Installation
Quick Start (Recommended)
Step 1: Install Globally
Open your terminal and run:
npm install -g atlas-pipeline-mcp
Step 2: Run Auto-Setup
Automatically configure your IDE (Cursor or VS Code):
atlas-mcp-setup
Step 3: Restart IDE
Restart your editor. The Atlas server will be automatically connected and ready to use.
Available Tools
Advanced Development & Analysis Tools
<table> <tr> <td width="30%"><code>atlas_bug_oracle</code></td> <td><b>Bug Oracle</b><br/>Predictive bug detection analyzing code patterns, complexity metrics, and historical data to forecast potential issues with 70-85% accuracy.</td> </tr> <tr> <td><code>atlas_code_whisperer</code></td> <td><b>Code Whisperer</b><br/>Context-aware code suggestions with pattern detection, best practice enforcement, and intelligent auto-completion.</td> </tr> <tr> <td><code>atlas_codebase_surgeon</code></td> <td><b>Codebase Surgeon</b><br/>Large-scale refactoring with dependency-aware modifications, impact analysis, and safe transformation strategies.</td> </tr> <tr> <td><code>atlas_semantic_search</code></td> <td><b>Semantic Search</b><br/>Natural language code search finding code by intent rather than keywords, with context understanding.</td> </tr> <tr> <td><code>atlas_smart_merge</code></td> <td><b>Smart Merge Resolver</b><br/>Intelligent git conflict resolution using code analysis and context to suggest optimal merge strategies.</td> </tr> <tr> <td><code>atlas_tech_debt</code></td> <td><b>Tech Debt Quantifier</b><br/>Measures and tracks technical debt with actionable metrics and prioritized remediation roadmaps.</td> </tr> </table>AI/ML Powered Tools
<table> <tr> <td width="30%"><code>atlas_rag_search</code></td> <td><b>RAG-Powered Semantic Search</b><br/>Natural language code search with knowledge graphs. Ask "how does auth work?" and get contextual results.</td> </tr> <tr> <td><code>atlas_ml_predict</code></td> <td><b>ML Bug & Performance Prediction</b><br/>Predict bugs before production with 70-85% accuracy. Analyzes complexity, churn, and code patterns.</td> </tr> <tr> <td><code>atlas_migrate</code></td> <td><b>Intelligent Code Migration</b><br/>Automated migration support for 12 types: JS→TS, React upgrades, Callbacks→Async, and more.</td> </tr> <tr> <td><code>atlas_testgen_advanced</code></td> <td><b>Advanced Test Generation</b><br/>Generate comprehensive test suites with edge cases, mocks, stubs, and 90%+ coverage projection.</td> </tr> </table>Core Pipeline & Analysis Tools
<table> <tr> <td width="30%"><code>atlas_pipeline</code></td> <td><b>Full Agentic Pipeline</b><br/>Complete workflow: Intent → Context → Decompose → Variants → Critique → Optimize</td> </tr> <tr> <td><code>atlas_intent</code></td> <td><b>Intent Analysis</b><br/>Extract actionable intent from natural language requests</td> </tr> <tr> <td><code>atlas_context</code></td> <td><b>Project Context Gathering</b><br/>Analyze project structure, dependencies, and file relationships</td> </tr> <tr> <td><code>atlas_git</code></td> <td><b>Git History Analysis</b><br/>Analyze commits, branches, file changes, and code evolution</td> </tr> <tr> <td><code>atlas_decompose</code></td> <td><b>Task Decomposition</b><br/>Break complex tasks into DAG (Directed Acyclic Graph) of subtasks</td> </tr> <tr> <td><code>atlas_variants</code></td> <td><b>Solution Variants</b><br/>Generate multiple implementation approaches with pros/cons analysis</td> </tr> </table>Quality & Optimization Tools
<table> <tr> <td width="30%"><code>atlas_review</code></td> <td><b>Automated Code Review</b><br/>Comprehensive analysis with quality scores, security checks, and best practice validation</td> </tr> <tr> <td><code>atlas_critique</code></td> <td><b>Code Critique</b><br/>Deep review for quality, security, performance, and maintainability</td> </tr> <tr> <td><code>atlas_optimize</code></td> <td><b>Code Optimization</b><br/>Apply improvements based on critique feedback and best practices</td> </tr> <tr> <td><code>atlas_refactor</code></td> <td><b>Smart Refactoring</b><br/>Code restructuring with complexity metrics and structural analysis</td> </tr> <tr> <td><code>atlas_security</code></td> <td><b>Security Scanner</b><br/>Detect vulnerabilities with CWE IDs and OWASP category mapping</td> </tr> </table>Senior Developer Tools
<table> <tr> <td width="30%"><code>atlas_senior_mentor</code></td> <td><b>Senior Mentor</b><br/>Architectural guidance from 15+ year veteran perspective with trade-off analysis and senior lessons</td> </tr> <tr> <td><code>atlas_performance_optimizer</code></td> <td><b>Performance Optimizer</b><br/>Deep performance analysis with Web Vitals optimization and bottleneck detection</td> </tr> <tr> <td><code>atlas_security_scanner</code></td> <td><b>Security Scanner Pro</b><br/>Enterprise-grade vulnerability detection with compliance assessment (GDPR, CCPA, HIPAA, PCI-DSS)</td> </tr> <tr> <td><code>atlas_state_architect</code></td> <td><b>State Management Architect</b><br/>Pattern comparison and scalability analysis for Redux, Zustand, Jotai, Recoil</td> </tr> <tr> <td><code>atlas_api_consultant</code></td> <td><b>API Design Consultant</b><br/>RESTful and GraphQL API design review with best practices and documentation templates</td> </tr> </table>UI/UX Design Tools
<table> <tr> <td width="30%"><code>atlas_ui_ux_designer</code></td> <td><b>UI/UX Designer</b><br/>Find best design inspirations online, generate multiple design options with images, and create production-ready code. Supports React, Vue, HTML, Svelte with accessibility guidance.</td> </tr> </table>Frontend Developer Tools
<table> <tr> <td width="30%"><code>atlas_performance_doctor</code></td> <td><b>Frontend Performance Doctor</b><br/>Detects React/Vue re-render issues, bundle bloat, memory leaks, Core Web Vitals issues. Provides specific code fixes with improvement estimates (e.g., "30-50% fewer re-renders").</td> </tr> <tr> <td><code>atlas_css_wizard</code></td> <td><b>CSS Architecture Wizard</b><br/>Analyzes CSS specificity conflicts, generates design tokens, converts between BEM/Tailwind/CSS Modules/styled-components/Emotion. Finds unused CSS and duplicates.</td> </tr> <tr> <td><code>atlas_animation_studio</code></td> <td><b>Animation Studio</b><br/>Professional animation generator with 30+ presets. Creates CSS keyframes, Framer Motion, GSAP, React Spring, and Anime.js code. Includes micro-interactions, scroll animations, and accessibility support.</td> </tr> <tr> <td><code>atlas_api_helper</code></td> <td><b>API Integration Helper</b><br/>Generates TypeScript types from API responses, React Query/SWR hooks, MSW mock handlers, Zod validation schemas, and complete API clients with error handling.</td> </tr> </table>Development Productivity Tools
<table> <tr> <td width="30%"><code>atlas_profiler</code></td> <td><b>Performance Profiling</b><br/>Detect bottlenecks, analyze time complexity (O(n), O(n²)), and memory usage</td> </tr> <tr> <td><code>atlas_test</code></td> <td><b>Test Case Generation</b><br/>Generate comprehensive tests for Jest, Vitest, Pytest, Mocha</td> </tr> <tr> <td><code>atlas_docs</code></td> <td><b>Auto Documentation</b><br/>Generate JSDoc, TSDoc, or PyDoc documentation automatically</td> </tr> <tr> <td><code>atlas_dependencies</code></td> <td><b>Dependency Analysis</b><br/>Detect unused packages, analyze dependencies, scan for vulnerabilities</td> </tr> <tr> <td><code>atlas_dashboard</code></td> <td><b>Metrics Dashboard</b><br/>Generate interactive HTML dashboards with real-time metrics</td> </tr> <tr> <td><code>atlas_explain</code></td> <td><b>Code Explanation</b><br/>Explain code with complexity analysis and pattern detection</td> </tr> <tr> <td><code>atlas_debug</code></td> <td><b>Smart Debugging</b><br/>Root cause analysis, stack trace parsing, and fix suggestions</td> </tr> <tr> <td><code>atlas_think</code></td> <td><b>Advanced Reasoning</b><br/>Sequential reasoning with branching logic for complex problems</td> </tr> </table>Utility Tools
<table> <tr> <td width="30%"><code>atlas_providers</code></td> <td><b>Provider Status</b><br/>Check available LLM providers and their current status</td> </tr> </table>Usage Guide
Once installed, interact with your AI Assistant (Copilot Chat or Cursor Chat). The appropriate tool is automatically activated based on your request.
Advanced Development Tools
| Goal | Example Request | Tool Used |
|---|---|---|
| Predict Bugs | "Analyze bug probability in this module" | atlas_bug_oracle |
| Get Code Suggestions | "Suggest improvements for this function" | atlas_code_whisperer |
| Large-Scale Refactoring | "Refactor the entire authentication system" | atlas_codebase_surgeon |
| Search by Intent | "Find where we handle payment processing" | atlas_semantic_search |
| Resolve Conflicts | "Help resolve this merge conflict intelligently" | atlas_smart_merge |
| Measure Tech Debt | "Quantify technical debt in this project" | atlas_tech_debt |
AI/ML Tools
| Goal | Example Request | Tool Used |
|---|---|---|
| Semantic Code Search | "Search for authentication code using RAG" | atlas_rag_search |
| Predict Issues | "Predict bug probability in payment-processor.ts" | atlas_ml_predict |
| Migrate Codebase | "Migrate this file from JavaScript to TypeScript" | atlas_migrate |
| Advanced Testing | "Generate comprehensive tests with edge cases" | atlas_testgen_advanced |
Professional Development Tools
| Goal | Example Request | Tool Used |
|---|---|---|
| Full Pipeline | "Run the pipeline on utils.ts to refactor it" | atlas_pipeline |
| Refactor Code | "Refactor this code and reduce complexity" | atlas_refactor |
| Performance Analysis | "Profile this code for performance bottlenecks" | atlas_profiler |
| Code Review | "Review this PR for quality and security" | atlas_review |
| Check Dependencies | "Analyze dependencies and find unused packages" | atlas_dependencies |
| Plan Feature | "Decompose the task of adding JWT auth" | atlas_decompose |
| Explore Solutions | "Generate 3 variants for this button component" | atlas_variants |
| Review Code | "Critique this code for security issues" | atlas_critique |
| Polish Code | "Optimize this function based on best practices" | atlas_optimize |
| Security Scan | "Scan this code for security vulnerabilities" | atlas_security |
| Generate Tests | "Generate tests for this authentication module" | atlas_test |
| Add Documentation | "Document this API with examples" | atlas_docs |
| Understand Code | "Explain how this algorithm works" | atlas_explain |
| Debug Error | "Debug this TypeError, here's the stack trace..." | atlas_debug |
| Complex Reasoning | "Think through how to design this system" | atlas_think |
| Project Context | "Analyze the project context and dependencies" | atlas_context |
Advanced Integration
Using Local LLMs
If you prefer running models locally (e.g., Ollama) or want to use your own API keys instead of your IDE's subscription, configure the server manually in your settings:
{
"atlas": {
"command": "npx",
"args": ["-y", "atlas-pipeline-mcp"],
"env": {
"OLLAMA_BASE_URL": "http://localhost:11434",
"OPENAI_API_KEY": "sk-...",
"ANTHROPIC_API_KEY": "sk-..."
}
}
}
Note: If no API keys are provided, Atlas defaults to Client Sampling mode, delegating generation to your IDE's AI capabilities.
Contributing
We welcome contributions to improve the Atlas pipeline.
- Repository: github.com/IamNishant51/atlas-mcp-server
- Issues: Report bugs or request features on GitHub
- Pull Requests: Submit improvements and new features
License
MIT License - see LICENSE file for details
Built by Nishant Unavane
For support, documentation, or questions, visit our GitHub repository.
常见问题
io.github.IamNishant51/atlas-pipeline 是什么?
提供 7 阶段 AI pipeline 的 MCP server:从 Intent、Context、Git 到分解、变体、批评与优化。
相关 Skills
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。