Code Intelligence MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Code Intelligence MCP Recommend a reusable component for user profile card"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Code Intelligence MCP
Intelligent code suggestion MCP service that provides AI-powered component and utility method recommendations for AI IDEs.
Introduction
This is an intelligent code suggestion service based on Model Context Protocol (MCP). It analyzes user requirements through AI and recommends the most suitable components and utility methods from private code repositories, helping developers improve code reuse and development efficiency.
Core Capabilities
🎨 UI Component Intelligent Recommendation
Analyze UI development requirements (pages, forms, interfaces, etc.)
Match the most relevant private components from the knowledge base
Generate optimized prompts with component imports and usage
Provide complete implementation guides and code examples
🔧 Utility Method Intelligent Recommendation
Analyze logic function requirements (data processing, format conversion, utility functions, etc.)
Find reusable utility methods from the method knowledge base
Generate optimized prompts with method imports and invocation
Avoid reinventing the wheel and improve code quality
Related MCP server: CodeWalker
Features
Intelligent Analysis Engine
Requirement Understanding: Deep understanding of user development intentions based on AI
Keyword Extraction: Automatically identify core elements in requirements
Complexity Assessment: Intelligently evaluate implementation difficulty and component fit
Knowledge Base Management
Component Knowledge Base: Manage private UI component library (props, events, slots, examples)
Method Knowledge Base: Manage utility method library (parameters, return values, types, usage)
Relevance Algorithm: Calculate recommendation scores based on semantic matching
Prompt Optimization
Bidirectional Optimization: Support prompt redesign for both component and method scenarios
Structured Output: Generate complete solutions including import statements and implementation steps
Best Practices: Integrate code standards and usage recommendations
Project Structure
code-intelligence-mcp/
├── src/
│ ├── core/ # Core functional modules
│ │ ├── knowledge-base.ts # Component knowledge base management
│ │ ├── utility-knowledge-base.ts # Utility method knowledge base management
│ │ ├── prompt-redesigner.ts # UI component prompt redesign
│ │ ├── logic-prompt-redesigner.ts # Logic method prompt redesign
│ │ ├── ai-suggester.ts # AI component recommendation engine
│ │ ├── ai-utility-suggester.ts # AI method recommendation engine
│ │ └── index.ts
│ ├── config/ # Configuration management
│ │ ├── model-manager.ts # AI model manager
│ │ ├── ai-client-adapter.ts # AI client adapter
│ │ ├── types.ts # Configuration type definitions
│ │ └── index.ts
│ ├── tools/ # MCP tool definitions
│ │ ├── suggestion.ts # Component suggestion tool
│ │ ├── utility-suggestion.ts # Method suggestion tool
│ │ ├── query.ts # Query tool
│ │ └── index.ts
│ ├── resources/ # MCP resource definitions
│ │ └── index.ts
│ ├── types/ # Type definitions
│ │ └── mcp-types.ts
│ ├── utils/ # Utility functions
│ │ ├── logger.ts # Logger utility
│ │ ├── ai-caller.ts # AI unified caller
│ │ ├── path-utils.ts # Path resolution utilities
│ │ └── index.ts
│ └── mcp-server.ts # MCP server main entry
├── ci-mcp-data/ # Configuration data (user-specific)
│ ├── components.example.json # UI component knowledge base example
│ ├── utils.example.json # Utility method knowledge base example
│ └── config.example.json # AI model configuration example
├── scripts/ # Script tools
│ ├── setup.js # Setup script
│ └── start.sh # Startup script
├── package.json
├── tsconfig.json
└── .npmignore # NPM publish exclusionsInstallation and Usage
Method 1: Use with npx (Recommended)
This is the recommended way for using the MCP server with AI IDEs like Claude Desktop.
Step 1: Prepare Configuration Files
Create a configuration directory (recommended location: ~/.config/ci-mcp):
mkdir -p ~/.config/ci-mcpDownload or create the following three configuration files:
config.json- AI model configurationcomponents.json- UI component knowledge baseutils.json- Utility method knowledge base
You can find example files in the npm package or repository.
Step 2: Configure AI IDE
Add to your AI IDE configuration (e.g., Claude Desktop's claude_desktop_config.json):
{
"mcpServers": {
"code-intelligence": {
"command": "npx",
"args": ["-y", "code-intelligence-mcp"],
"env": {
"CI_MCP_DATA_DIR": "~/.config/ci-mcp"
}
}
}
}Environment Variables:
CI_MCP_DATA_DIR(Recommended): Specify the configuration directory, all three files will be loaded from this directoryCI_MCP_CONFIG: Directly specify the path toconfig.jsonCI_MCP_COMPONENTS: Directly specify the path tocomponents.jsonCI_MCP_UTILS: Directly specify the path toutils.json
Path Formats Supported:
Absolute path:
/Users/xxx/.config/ci-mcpHome directory:
~/.config/ci-mcpor$HOME/.config/ci-mcpEnvironment variables:
${MY_CONFIG_DIR}/ci-mcp
Step 3: Restart AI IDE
Restart your AI IDE (e.g., Claude Desktop), and the MCP service will start automatically via npx.
Method 2: Local Development
Prerequisites
Configure Knowledge Base Data Files
The project requires manual configuration of the following data files in ci-mcp-data/ directory:
ci-mcp-data/config.json- AI model configuration (including API Key)cp ci-mcp-data/config.example.json ci-mcp-data/config.json # Edit config.json and fill in your API Keyci-mcp-data/components.json- UI component knowledge basecp ci-mcp-data/components.example.json ci-mcp-data/components.json # Edit components.json based on your private component libraryAdd component information following the existing format:
description,import,relativePath, etc.
ci-mcp-data/utils.json- Utility method knowledge basecp ci-mcp-data/utils.example.json ci-mcp-data/utils.json # Edit utils.json based on your utility method libraryInclude method information:
description,import,params,returns, etc.
Note:
config.jsoncontains sensitive information (API Key) and is added to.gitignore, will not be committed to the repositorycomponents.jsonandutils.jsonneed to be configured based on your actual code repositoryRefer to example files like
config.example.jsonfor configuration format
Install Dependencies
pnpm installDevelopment Mode
pnpm devBuild
pnpm buildProduction Mode
pnpm start:prodMCP Tools
🎨 UI Component Suggestion Tools
1. suggest_components
Intelligently analyze UI development requirements and recommend the most suitable private components.
Use Cases:
Create pages, forms, interfaces and other UI features
Quick development using private component library
Get complete implementation solutions
Input Parameters:
{
prompt: string; // User requirement description, e.g. "Create user login page"
}Output:
Requirement Analysis: Keywords, component types, complexity assessment
Suggested Components: Component list + relevance score + recommendation reason
Optimized Prompt: Including specific component imports and usage
Implementation Guide: Step-by-step development suggestions
Example:
// Input
{"prompt": "Generate a user information edit form"}
// Output
{
"analysis": {
"keywords": ["form", "edit", "user information"],
"componentTypes": ["form", "input", "button"]
},
"suggestedComponents": [
{
"name": "das-form",
"relevance": 0.95,
"reason": "Most suitable for user information editing scenarios"
}
],
"redesignedPrompt": "Create using das-form component...",
"implementationGuide": "1. Import component...\n2. Configure form fields..."
}2. query_component
Query detailed information of a specific component.
Input Parameters:
{
componentName: string; // Component name, e.g. "das-button"
}Output:
Component description, category, tags
Props parameter list
Events list
Slots description
Usage example code
Import path
🔧 Utility Method Suggestion Tools
1. suggest_utilities
Intelligently analyze logic development requirements and recommend reusable utility methods.
Use Cases:
Implement data processing and format conversion functions
Need encryption, validation and other utility functions
Avoid reinventing the wheel
Input Parameters:
{
prompt: string; // Logic requirement description, e.g. "Need to format numbers with thousand separators"
}Output:
Requirement Analysis: Key function points, method types
Suggested Methods: Method list + relevance score + recommendation reason
Optimized Prompt: Including method imports and invocation
Implementation Guide: Usage steps and notes
Example:
// Input
{"prompt": "Implement password encryption function"}
// Output
{
"analysis": {
"keywords": ["encryption", "password", "security"],
"methodTypes": ["encryption", "security"]
},
"suggestedUtilities": [
{
"name": "encryptPassword",
"relevance": 0.98,
"reason": "Provides MD5/SHA256 password encryption"
}
],
"redesignedPrompt": "Use encryptPassword method...",
"implementationGuide": "1. Import method...\n2. Call encryption..."
}2. query_utility
Query detailed information of a specific utility method.
Input Parameters:
{
utilityName: string; // Method name, e.g. "formatNumber"
}Output:
Method description, category, type
Parameter list (parameter name, type, description)
Return value type and description
Usage example code
Import path
MCP Resources
code-intelligence://component-library
Component Library Resource
Provides complete private component library information, including:
List of all available components
Component categories and tags
Component capability overview
code-intelligence://utility-library
Utility Method Library Resource
Provides complete utility method library information, including:
List of all available methods
Method categories and functions
Method capability overview
code-intelligence://usage-guide
Usage Guide Resource
Includes:
MCP tools usage instructions
Best practice recommendations
FAQs
Integration configuration guide
Tech Stack
Core Framework
TypeScript - Type-safe development
Node.js - Runtime environment
MCP SDK (@modelcontextprotocol/sdk) - Model Context Protocol implementation
AI Integration
Vercel AI SDK - Unified AI interface
OpenAI - GPT series model support
Anthropic - Claude series model support
DeepSeek - Domestic large model support
Development Tools
pnpm - Package manager
tsx - TypeScript executor
ESLint + Prettier - Code standards
Husky - Git hooks
Development Standards
Use TypeScript for type-safe development
Follow ESLint and Prettier code standards
Use Husky for Git hooks management
Configuration
1. MCP Service Configuration (mcp-config.json)
Register MCP service in AI IDE:
{
"mcpServers": {
"code-intelligence": {
"command": "/bin/zsh",
"args": ["/path/to/code-intelligence-mcp/scripts/start.sh"]
}
}
}2. AI Model Configuration (data/config.json)
Configure AI models used by the recommendation engine:
{
"defaultModel": "claude-3-7-sonnet-latest",
"providers": [
{
"provider": "anthropic",
"models": [
{
"model": "claude-3-7-sonnet-latest",
"title": "Claude 3.7 Sonnet",
"baseURL": "https://api.302.ai/v1",
"apiKey": "your-api-key"
}
]
},
{
"provider": "openai",
"models": [
{
"model": "gpt-4o",
"title": "GPT-4o",
"baseURL": "https://api.openai.com/v1",
"apiKey": "your-api-key"
}
]
}
]
}Configuration Description:
defaultModel: Default model name to use, must exist inprovidersproviders: List of supported AI providersprovider: Provider type (anthropic,openai,deepseek,ollama)models: List of model configurations for this providermodel: Model name (must matchdefaultModel)title: Model display namebaseURL: API endpoint addressapiKey: API key
Supported Providers:
anthropic- Claude series modelsopenai- GPT series modelsdeepseek- DeepSeek domestic modelsollama- Local models
3. Knowledge Base Data
Component Knowledge Base (data/components.json)
{
"components": [
{
"name": "das-button",
"description": "Button component",
"category": "Basic component",
"tags": ["button", "interaction"],
"props": [...],
"events": [...],
"example": "..."
}
]
}Utility Method Knowledge Base (data/utils.json)
{
"utilities": [
{
"name": "formatNumber",
"description": "Format number with thousand separators",
"category": "Formatting",
"type": "formatter",
"params": [...],
"returns": {...},
"example": "..."
}
]
}License
MIT
Contributing
We welcome contributions! Please see CONTRIBUTING.md for details on how to contribute to this project.
Changelog
See CHANGELOG.md for version history and release notes.
Available Tools
4 toolsquery_componentA
根据组件名称查询详细信息,包括 props、events、slots、使用示例等。用于了解推荐组件的具体用法。
Inputs: componentName (required).
query_utilityA
根据工具方法名称查询详细信息,包括参数、返回值、使用示例等。用于了解推荐工具方法的具体用法。
Inputs: utilityName (required).
suggest_componentsA
USE WHEN: 用户想要创建/生成/新建/开发页面、组件或界面时。分析用户需求,从私有组件库@private-basic-components中智能推荐最合适的组件,生成包含具体实现建议的优化提示词。自动触发场景:"创建页面"、"生成组件"、"新建界面"、"开发表单"、"实现功能"等所有UI开发任务。
Inputs: prompt (required).
suggest_utilitiesA
USE WHEN: 用户想要实现某些逻辑功能、数据处理、格式转换、工具函数等时。分析用户的逻辑需求,从工具方法库中智能推荐可以直接复用的方法,避免重复开发。自动触发场景:"实现数据格式化"、"需要加密功能"、"时间处理"、"IP校验"、"数据转换"等所有逻辑开发任务。
Inputs: prompt (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: suggesting components vs. utilities, and querying component vs. utility details. There is no overlap or ambiguity between the four tools.
All tool names follow a consistent verb_noun pattern: suggest_components, query_component, suggest_utilities, query_utility. The naming is uniform and predictable.
With exactly 4 tools, the set is well-scoped for the server's purpose of suggesting and querying components and utilities. Each tool earns its place without redundancy.
The tool surface covers the full lifecycle for the stated domain: suggestion (discovery) and query (details) for both components and utilities. There are no obvious gaps for the intended use case.
Related MCP Connectors
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
MCP server for building and testing AI agents with multi-model experimentation and insights.
GitHub Copilot MCP: code, repo, PR, workflow tools for AI assistants.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that analyzes codebases and generates contextual prompts, making it easier for AI assistants to understand and work with code repositories.19MIT
- AlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that indexes Python codebase structures to help AI assistants discover and reuse existing functions instead of duplicating code. It enables real-time searching of function metadata, duplicate detection, and structural analysis across multiple projects.-

flyto-indexerofficial
AlicenseNot gradedqualityAmaintenanceMCP server that gives AI assistants impact analysis, cross-project reference tracking, and code health scoring.93 PyPI4Apache 2.0- AlicenseCqualityDmaintenanceAn MCP server that analyzes local or remote GitHub repositories, providing intelligent code context and structure to AI coding assistants.1013MIT