Skip to main content
Glama

Mind Map MCP Server v1.22.0

Experimental Code Intelligence Platform - A Model Context Protocol (MCP) server that explores neuroscience-inspired approaches to software development analysis. This is an experimental research project featuring advanced query caching, associative learning patterns, context awareness, attention mechanisms, temporal knowledge modeling, and code analysis tools.

โš ๏ธ Current Status: Experimental v1.22.0

๐Ÿงช This is experimental software under active development - Use for testing and research purposes. Features may change or be removed.

Features under development: Context-aware caching โ€ข Brain-inspired learning โ€ข Code pattern detection โ€ข Document analysis โ€ข Multi-language AST parsing โ€ข File ignore patterns โ€ข CI/CD automation โ€ข Memory optimization

๐ŸŽฏ Latest Update v1.22.0: Cross-Language API Detection - Comprehensive API endpoint detection across 12 programming languages. New Features: Detect REST APIs (Flask, Express, Spring Boot), GraphQL schemas, gRPC services, WebSocket endpoints, and WebAssembly modules. Language Support: Python, JavaScript/TypeScript, Java, Go, Rust, C++, C#, PHP, Ruby, Swift, Kotlin, and Scala. Intelligent Detection: Framework-specific patterns with confidence scoring for accurate API discovery. New dedicated MCP tool detect_cross_language_apis for direct API analysis.

Related MCP server: codeweave-mcp

โš ๏ธ Important Disclaimer

This is experimental software developed for research and testing purposes. It explores various approaches to code analysis and project understanding using Model Context Protocol (MCP).

Before using:

  • Expect bugs, incomplete features, and breaking changes

  • Use in non-production environments only

  • Backup your projects before extensive use

  • Report issues and provide feedback to help improve the project

Use cases:

  • Improving coding workflows with Claude Code - Enhanced project understanding and context

  • Experimenting with MCP server development

  • Testing code analysis and pattern detection approaches

  • Research into alternative programming assistance tools

  • Learning about AST parsing and project structure analysis

๐Ÿ“ฆ Installation & Setup

Quick Install from npm

# Install globally
npm install -g mind-map-mcp

# Or install locally in your project
npm install mind-map-mcp

Claude Code Integration

1. Automatic Setup (Recommended)

The easiest way to set up Mind Map MCP with Claude Code:

# Run the automatic setup tool
npx mind-map-mcp init-claude-code

# Or if installed globally
mind-map-mcp init-claude-code

This automatically:

  • โœ… Detects your operating system and Claude installation

  • โœ… Creates proper configuration files with correct paths

  • โœ… Provides platform-specific setup instructions

  • โœ… Includes verification commands and troubleshooting

2. Manual Setup for Claude Desktop

If you prefer manual configuration, add this to your Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json Linux: ~/.config/claude-desktop/config.json

{
  "mcpServers": {
    "mind-map-mcp": {
      "command": "npx",
      "args": ["mind-map-mcp"],
      "env": {}
    }
  }
}

3. Environment Variable Configuration

You can configure the MCP server to work with specific project directories using the MCP_PROJECT_ROOT environment variable:

{
  "mcpServers": {
    "mind-map-mcp": {
      "command": "npx",
      "args": ["mind-map-mcp"],
      "env": {
        "MCP_PROJECT_ROOT": "/path/to/your/project"
      }
    }
  }
}

What it does:

  • Makes MCP scan and cache files in the specified project directory

  • Creates .mindmap-cache folder in the target project

  • Uses project-specific configuration and mind map data

  • Allows working with multiple projects independently

Usage Examples:

// For a specific project
"env": {
  "MCP_PROJECT_ROOT": "/Users/yourname/projects/my-app"
}

// For a demo or test project
"env": {
  "MCP_PROJECT_ROOT": "/Users/yourname/projects/demo-project"
}

Without this variable: MCP uses the current working directory where the MCP server was started.

4. Verify Installation

After setup, restart Claude and verify the integration:

  1. Check MCP Tools: In Claude, you should see 33 new MCP tools available

  2. Test Basic Functionality: Try these commands in Claude:

    Please scan the current project and show me the statistics.
  3. Test Features: Try experimental features:

    Please analyze the project architecture.

๐Ÿ“ Usage with Claude Code

Once installed, you can experiment with these commands in Claude:

Sample Workflow

# Start with basic scanning:
Please scan the project and get initial statistics.

# Explore analysis features:
Please analyze the project structure and suggest areas of focus.

# Test learning features:
Please update the mind map with information about [task description].

๐Ÿ”ฌ Experimental Analysis Features

# Hebbian Learning - "Neurons that fire together, wire together"
Please show me the Hebbian learning statistics and top co-activation patterns.

# Hierarchical Context - Multi-level awareness
Please get the hierarchical context stats and most relevant context items.

# Attention System - Dynamic focus allocation
Please show the attention system statistics and allocate attention to important nodes.

# Bi-temporal Knowledge - Valid vs Transaction time tracking
Please get bi-temporal statistics and create a context window for this session.

# Pattern Prediction - Anticipatory intelligence
Please get pattern predictions and show emerging patterns.

Advanced Intelligence Features

# Get architectural insights
Please analyze the project architecture and detect design patterns.

# Find cross-language dependencies
Please detect cross-language dependencies in this polyglot project.

# Get intelligent refactoring suggestions
Please generate multi-language refactoring suggestions focused on architecture.

# Predict emerging code patterns
Please analyze and predict what code patterns are likely to emerge.

Development Tool Integration

# Detect available tools
Please detect all development tools available in this project.

# Run comprehensive analysis
Please run the full tool suite and provide aggregated results.

# Get tool recommendations
Please recommend missing development tools that would benefit this project.

๐Ÿ“‹ Verification Checklist

โœ… Installation: npm list -g mind-map-mcp shows the package โœ… Claude Integration: 33 MCP tools visible in Claude โœ… Basic Functionality: scan_project command works โœ… Advanced Features: Brain-inspired tools respond correctly โœ… Multi-language Support: AST analysis works for your languages

๐Ÿ”ง Troubleshooting

Common Issues:

  1. "No MCP tools visible" โ†’ Restart Claude after configuration

  2. "Command not found" โ†’ Ensure npm global install path is in PATH

  3. "Permission denied" โ†’ Run npm config get prefix and check permissions

  4. "Server not responding" โ†’ Check Claude Desktop config file syntax

Get Help:

Features

๐Ÿง  Brain-Inspired Intelligence (Phase 6)

  • Associative Memory System: Neural activation spreading across connected code concepts (50-70% relevance improvement)

  • Context-Aware Query Caching: Intelligent caching with similarity matching (5-10x performance boost for repeated queries)

  • Parallel Processing Engine: Chunked file analysis with worker pool orchestration (3-5x faster project scanning)

  • Neuromorphic Query Patterns: Replaces linear search with brain-like associative activation networks

  • Intelligent Cache Invalidation: Path-based selective cache clearing with LRU eviction and 100MB memory management

  • Hebbian Learning System: Co-activation tracking with synaptic strengthening ("neurons that fire together, wire together")

  • Inhibitory Learning: Failure avoidance through negative pattern recognition (30% reduction in repeated mistakes)

  • Hierarchical Context Management: Multi-level context awareness (immediate, session, project, domain)

  • Attention Mechanisms: Multi-modal attention fusion with cognitive load management (Miller's 7ยฑ2 rule)

  • Bi-temporal Knowledge Model: Valid time vs transaction time tracking with complete audit trails

  • Pattern Prediction Engine: Anticipates code patterns before they emerge using time series analysis and predictive forecasting

๐Ÿš€ Memory Optimization (v1.15.0)

  • Variable Lazy Loading: Intelligent memory management with 40.3% reduction in variable node memory usage

  • Smart Filtering: Only loads critical variables (exported, global, heavily-used >5 references) immediately

  • Summary Node System: Creates single nodes containing lazy-loaded variable metadata for thousands of variables

  • On-Demand Loading: 8ms average retrieval time for pattern-based variable queries

  • Full Functionality Preservation: All variable querying capabilities maintained while dramatically reducing memory footprint

  • Automatic Optimization: No configuration required - automatically detects important vs. lazily-loadable variables

๐Ÿ“Š Advanced Call Pattern Analysis (v1.1.5)

  • Function Call Graph Construction: Complete call graph analysis with entry points, cycles, and depth calculation

  • Constructor Call Detection: Accurate detection of class instantiation and constructor patterns

  • Method Call Analysis: Comprehensive tracking of method invocations and chaining patterns

  • Async/Await Pattern Recognition: Full support for asynchronous call pattern detection

  • Recursion Detection: Automatic identification of recursive functions and call cycles

  • Code Style Recognition: Comprehensive naming convention and style pattern analysis

  • Complexity Calculation: Enhanced cyclomatic complexity with callback function and control flow analysis

  • Cross-File Pattern Resolution: Advanced resolution of call patterns across multiple files

๐Ÿš€ CI/CD Pipeline Infrastructure (v1.1.5)

  • Automated Testing: Comprehensive test suite with multi-language AST validation

  • Security Scanning: Automated vulnerability detection with npm audit integration

  • Performance Monitoring: Continuous performance benchmarking with alert thresholds

  • Code Quality Analysis: Bundle size monitoring, style analysis, and quality reporting

  • Release Automation: Automated NPM publishing with GitHub release creation

  • Maintenance Workflows: Dependency updates, health checks, and system monitoring

  • Pull Request Validation: PR title validation, impact analysis, and comprehensive testing

๐Ÿ“ Enhanced File Ignore Configuration (v1.6.0)

  • Multi-Source Pattern Loading: Intelligent pattern merging from defaults, .gitignore, .mindmapignore, and custom configuration

  • Real-Time Pattern Testing: Live pattern validation with performance metrics and file matching preview

  • Pattern Analytics & Statistics: Comprehensive stats on pattern effectiveness, scan time reduction, and filtering efficiency

  • Smart Default Patterns: 30 intelligent default patterns for common file types (node_modules, build artifacts, etc.)

  • Configuration Management API: 3 new MCP tools for dynamic pattern updates and testing

  • Developer-Friendly Interface: Familiar .gitignore syntax with enhanced capabilities and precedence rules

  • Performance Optimization: 33% file filtering efficiency with 8-12ms pattern loading for improved scan performance

  • Framework-Specific Patterns: Language and framework-specific ignore patterns (*.pyc, *.class, target/, dist/)

๐Ÿง  Advanced Code Intelligence

  • Multi-Language AST Analysis: Full parsing for 12 languages (TypeScript/JavaScript/Python/Java/Go/Rust/C++/PHP/C#/Ruby/Swift/Kotlin/Scala) with function/class extraction

  • Dynamic Import Detection: Track runtime imports including import() calls, require() statements, template literals, and variable-based module loading for modern JavaScript/TypeScript applications

  • Method Call Chain Analysis: Advanced call sequence tracking following Aโ†’Bโ†’Cโ†’D execution paths up to 10 levels deep with performance impact assessment and risk analysis

  • Variable Usage Tracking: Comprehensive variable intelligence tracking declaration, usage, and modification patterns across files with lifecycle analysis and cross-module dependency detection

  • Cross-Language Dependency Detection: Identifies API calls, FFI, microservices, and shared data patterns across languages

  • Polyglot Project Analysis: Architectural style detection with multi-language recommendations

  • Enterprise Framework Detection: React, Vue, Express, Django, Flask, Spring Boot, Laravel, ASP.NET, Rails, SwiftUI, Android, Akka, and 60+ more

  • Architectural Pattern Detection: 7 pattern types with multi-language interoperability analysis

  • Predictive Error Detection: Risk analysis system with language-specific pattern matching

  • Intelligent Fix Suggestions: Context-aware recommendations with cross-language insights

๐Ÿ”ง Integrated Development Tooling

  • 100+ Development Tools: Complete tooling ecosystem across 12 languages with intelligent detection

  • Smart Tool Execution: Run tests, linters, formatters, and security scanners with issue parsing

  • Intelligent Recommendations: Get suggestions for missing tools with installation commands

  • Tool Suite Orchestration: Run multiple tools in parallel with aggregated results

  • Issue Classification: Parse and categorize tool outputs for actionable insights

  • Mind Map Integration: Store tool results as nodes/edges for learning and correlation

๐ŸŽฏ Enhanced Framework Detection

  • 25+ Framework Detection: Comprehensive framework analysis across 6 categories with confidence scoring

  • Web Frameworks: React, Vue, Angular, Express, Django, Flask, Spring Boot, Next.js, Nuxt.js detection

  • Mobile Frameworks: React Native, Flutter, Xamarin with platform-specific pattern analysis

  • Desktop Frameworks: Electron, Tauri, Qt with configuration and build system detection

  • Game Engines: Unity, Unreal Engine, Godot with project structure and script analysis

  • ML/AI Frameworks: TensorFlow, PyTorch, scikit-learn with usage pattern detection

  • Cloud Platforms: Docker, Kubernetes with manifest analysis and deployment patterns

๐Ÿ“š Advanced Learning System

  • Task Outcome Learning: Tracks success/failure patterns with confidence scoring

  • Error Pattern Recognition: Categorizes errors and maps to successful solutions

  • Cross-Session Intelligence: Maintains knowledge between Claude Code sessions

  • Performance Learning: Adaptive optimization based on usage patterns

  • Solution Effectiveness Tracking: Measures and improves recommendation quality

๐Ÿ” Enterprise Query System

  • Cypher-like Graph Queries: Advanced querying with complex filtering and relationships

  • Temporal Analysis: Code evolution tracking and change impact analysis

  • Aggregate Analytics: Project insights, metrics, and trend analysis

  • Semantic Search: Multi-factor relevance scoring with confidence weighting

  • Saved Queries: Template system for common analysis patterns

โšก Performance & Scalability

  • Multi-Index Storage: Optimized indexing for type, path, name, confidence, framework, language

  • LRU Caching: Memory optimization with intelligent cache management

  • Performance Monitoring: Real-time operation timing and bottleneck detection

  • Query Optimization: Execution planning and index hints for complex queries

Installation

# Clone or create the project
npm install

# Build the server
npm run build

# Test the installation
npm start

Usage with Claude Code

The easiest way to get started is to use the built-in initialization method:

# After installing and building, run any Claude Code session and use:
mcp://mind-map-mcp/init_claude_code

# Or for specific setups:
mcp://mind-map-mcp/init_claude_code?setup_type=desktop&platform=macos
mcp://mind-map-mcp/init_claude_code?setup_type=cli&platform=linux

This automatically generates:

  • โœ… Platform-specific configuration files with correct paths

  • โœ… Ready-to-copy JSON configurations for Claude Desktop/CLI

  • โœ… Complete setup checklist with verification commands

  • โœ… Quick start workflow with essential commands

  • โœ… Troubleshooting guide for common issues

  • โœ… CLAUDE.md template for project-specific instructions

Manual Configuration

If you prefer manual setup, add this server to your Claude Code MCP configuration:

Claude Desktop Configuration

Edit your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mind-map-mcp": {
      "command": "node",
      "args": ["/path/to/mind-map-mcp/dist/index.js"],
      "env": {}
    }
  }
}

CLI Usage

# Start the server directly (for testing)
npm start

# Or use the built binary
node dist/index.js

Available MCP Tools (27 Total)

Core Intelligence Tools

  • scan_project: Initial project analysis with AST parsing and pattern detection

  • query_mindmap: Semantic search with confidence scoring and relevance ranking

  • update_mindmap: Learning system for task outcomes and error patterns

  • suggest_exploration: Intelligent file/function recommendations

  • get_context: Project overview and contextual information

  • get_stats: Comprehensive project statistics and metrics

Advanced Analysis Tools

  • predict_errors: Risk analysis and error prediction based on patterns

  • suggest_fixes: Context-aware fix recommendations for error patterns

  • analyze_architecture: Detect architectural patterns and design insights

  • advanced_query: Cypher-like graph queries with complex filtering

  • temporal_query: Code evolution and change impact analysis

  • aggregate_query: Project metrics, insights, and trend analysis

Performance & Utility Tools

  • get_performance: Real-time performance monitoring and bottleneck detection

  • get_cache_stats: Query cache performance metrics and memory usage statistics

  • clear_cache: Intelligent cache invalidation with selective path-based clearing

  • save_query: Save and manage reusable query templates

  • execute_saved_query: Run saved queries with parameter substitution

  • get_insights: Comprehensive project insights with actionable recommendations

Multi-Language Intelligence Tools

  • detect_cross_language_deps: Identify cross-language dependencies and communication patterns

  • analyze_polyglot_project: Analyze multi-language project structure and architecture

  • generate_multi_language_refactorings: Generate refactoring suggestions for polyglot codebases

Development Tooling Integration

  • detect_project_tooling: Detect available development tools across all languages in the project

  • run_language_tool: Execute specific development tools with intelligent issue parsing

  • get_tooling_recommendations: Get intelligent recommendations for missing development tools

  • run_tool_suite: Run multiple development tools in parallel with aggregated results

Enhanced Framework Detection

  • detect_enhanced_frameworks: Comprehensive framework detection across web, mobile, desktop, game, ML/AI, and cloud categories

  • get_framework_recommendations: Get intelligent recommendations based on detected frameworks and project patterns

Example Usage

{
  "name": "scan_project",
  "arguments": {
    "force_rescan": false,
    "include_analysis": true,
    "ast_analysis": true
  }
}
{
  "name": "advanced_query", 
  "arguments": {
    "query": "MATCH (f:file)-[:contains]->(func:function) WHERE func.name CONTAINS 'auth' RETURN f.path, func.name",
    "limit": 10
  }
}
{
  "name": "predict_errors",
  "arguments": {
    "file_path": "src/auth/login.ts",
    "context": "implementing OAuth integration"
  }
}

How It Works

1. Advanced Project Analysis

The server performs comprehensive scanning and creates nodes for:

  • Files & Directories: Complete project structure with metadata

  • AST Elements: Functions, classes, interfaces, imports/exports with full signatures

  • Architectural Patterns: 7 pattern types with confidence scoring

  • Framework Detection: React, Vue, Express, Django, Flask, pandas, NumPy, etc.

  • Error Patterns: Historical error categorization and solution mapping

2. Multi-Language AST Parsing

Full support for 12 major programming languages:

Original Languages:

  • TypeScript/JavaScript: Complete AST with function/class extraction via TypeScript compiler API

  • Python: Full AST parsing with subprocess execution for functions, classes, decorators

  • Java: Complete AST parsing with java-parser for classes, methods, annotations, Spring Boot detection

  • Go: Go AST parsing with struct/interface/function extraction and framework detection

  • Rust: Rust AST analysis with struct/trait/impl extraction and crate dependency mapping

  • C/C++: C++ parsing with class/function/template extraction and build system analysis

NEW Languages (v1.1.4):

  • PHP: Complete AST with class/method extraction and Laravel/Symfony framework detection

  • C#: Full AST parsing with ASP.NET/Entity Framework detection and namespace analysis

  • Ruby: Ruby AST with class/method extraction and Rails/Sinatra framework detection

  • Swift: Swift AST parsing with UIKit/SwiftUI framework detection and protocol analysis

  • Kotlin: Kotlin AST with Android/Compose framework detection and coroutine analysis

  • Scala: Scala AST parsing with Akka/Play framework detection and trait analysis

3. Brain-Inspired Intelligence (Phase 6) ๐Ÿง 

Revolutionary neuromorphic computing principles applied to code intelligence:

  • Associative Memory Networks: Neural activation spreading replaces linear search (50-70% relevance improvement)

  • Context-Aware Caching: Intelligent similarity matching with LRU eviction (5-10x performance boost)

  • Parallel Processing Engine: Worker pool orchestration with chunked analysis (3-5x faster scanning)

  • Neuromorphic Query Patterns: Brain-like activation across connected code concepts

  • Intelligent Memory Management: 100MB cache with path-based invalidation and exponential decay

  • Episodic Memory System (NEW v1.1.4): Store and retrieve programming experiences with 77.1% similarity matching accuracy and experience-based suggestions with 81.1% confidence

4. Intelligent Learning System

As you use Claude Code, the server:

  • Tracks Task Outcomes: Success/failure patterns with confidence adjustment

  • Maps Error Solutions: Categorizes errors and associates with successful fixes

  • Builds Pattern Recognition: Framework usage, naming conventions, architectural insights

  • Optimizes Performance: LRU caching and multi-index storage for faster queries

5. Enterprise Query Engine

Advanced querying capabilities include:

  • Cypher-like Syntax: Complex graph traversal with filtering and aggregation

  • Semantic Search: Multi-factor relevance scoring (exact, path, confidence, recency)

  • Temporal Analysis: Code evolution tracking and change impact assessment

  • Predictive Analytics: Error risk assessment and fix suggestion engine

6. Cross-Session Intelligence

All learning persists locally with:

  • Graph Database: Nodes, edges, and relationship storage in JSON format

  • Performance Monitoring: Operation timing and bottleneck detection

  • Query Optimization: Execution planning and index hints

  • Cache Management: LRU eviction and intelligent memory optimization

Data Storage

The mind map data is stored locally in your project directory:

your-project/
โ”œโ”€โ”€ .mindmap-cache/
โ”‚   โ””โ”€โ”€ mindmap.json          # Serialized knowledge graph
โ””โ”€โ”€ ... (your project files)

Privacy & Security

  • Local-Only: All data stays on your machine

  • No Network: No external API calls or data transmission

  • Configurable: Choose what gets tracked

  • Transparent: All data stored in readable JSON format

Development

# Development with auto-rebuild
npm run dev

# Type checking
npm run type-check

# Linting
npm run lint

# Testing
npm test

Architecture

The server consists of several key components:

  • MindMapEngine: Core intelligence and query processing

  • MindMapStorage: Graph database operations and persistence

  • FileScanner: Project analysis and file classification

  • MCP Server: Protocol implementation and tool handling

Roadmap

โœ… Completed (Phases 1-5.9)

  • Core MCP Server: 25 tools with stdio transport

  • Multi-Language AST Analysis: 12 languages (TypeScript/JavaScript/Python/Java/Go/Rust/C++/PHP/C#/Ruby/Swift/Kotlin/Scala) with comprehensive parsing

  • Cross-Language Intelligence: Dependency detection, polyglot analysis, multi-language refactoring

  • Development Tooling Integration: 100+ tools across 12 languages with intelligent execution and parsing

  • Enhanced Framework Detection: 60+ frameworks across 6 categories (web, mobile, desktop, game, ML/AI, cloud)

  • Advanced Intelligence: Predictive errors, fix suggestions, architectural patterns, risk analysis

  • Enterprise Querying: Cypher-like queries, temporal analysis, aggregates, saved queries

  • Performance Systems: Multi-index storage, LRU caching, monitoring, insights

๐Ÿšง Completed Multi-Language Support (Phase 5)

  • Phase 5.1: โœ… Python AST support with Flask/Django detection

  • Phase 5.2: โœ… Java AST support with Spring Boot/Maven/Gradle detection

  • Phase 5.3: โœ… Go AST support with Gin/Echo framework detection

  • Phase 5.4: โœ… Rust AST support with Actix/Tokio/Serde detection

  • Phase 5.5: โœ… C/C++ AST support with Qt/Boost/CMake detection

  • Phase 5.7: โœ… Multi-Language Intelligence with cross-language dependency detection

  • Phase 5.8: โœ… Language-Specific Tooling Integration with 80+ development tools

  • Phase 5.9: โœ… Enhanced Framework Detection across 6 categories with 25+ frameworks

๐Ÿ“‹ Version History

v1.4.0 (Current) ๐Ÿš€

  • โœ… Enhanced Query System: Comprehensive improvements to core query functionality

  • โœ… Multi-Word Query Support: Perfect handling of queries like "mind map", "pattern analysis"

  • โœ… Semantic Language Mapping: "typescript" finds .ts files, "javascript" finds .js files

  • โœ… Exact File Path Matching: Direct file queries like "src/core/MindMapEngine.ts"

  • โœ… Advanced CamelCase Handling: Full support for camelCase, PascalCase, and mixed case queries

  • โœ… Improved Temporal Queries: Enhanced time-based analysis with evolution metrics

  • โœ… Better Advanced Query Engine: Cypher-like syntax improvements for complex graph queries

  • โœ… Enhanced Aggregate Queries: Improved grouping and field extraction for statistical analysis

v1.3.1

  • โœ… Fixed Java Code Structure Recognition: Resolved Java class/method extraction issues

  • โœ… Enhanced Java AST Parsing: Complete Java file code intelligence with proper node separation

v1.1.5

  • โœ… Advanced Call Pattern Analysis: Complete function call graph construction with 100% test success rate

  • โœ… Constructor Call Detection: Accurate class instantiation and constructor pattern recognition

  • โœ… Enhanced Complexity Calculation: Improved cyclomatic complexity with callback functions and control flow

  • โœ… Code Style Recognition: Comprehensive naming convention and style pattern analysis (camelCase, PascalCase, snake_case)

  • โœ… CI/CD Pipeline Infrastructure: Complete automation with testing, security scanning, and performance monitoring

  • โœ… Release Automation: Automated NPM publishing with GitHub release workflows

  • โœ… Pull Request Validation: Comprehensive PR checks with impact analysis and quality gates

v1.1.4

  • โœ… 12 Programming Languages + Episodic Memory System

  • โœ… Added comprehensive support for PHP, C#, Ruby, Swift, Kotlin, and Scala

  • โœ… Complete AST parsing and framework detection

  • โœ… Brain-inspired episodic memory with 77.1% similarity matching accuracy

v1.1.0-1.1.3

  • โœ… Multi-modal confidence fusion and brain-inspired intelligence platform

  • โœ… Performance optimization and cache improvements

  • โœ… Enhanced query description with semantic search capabilities

v1.0.1

  • โœ… Enhanced README with comprehensive Claude Code integration guide

  • โœ… Added step-by-step installation instructions

  • โœ… Included usage examples and workflow guides

  • โœ… Added troubleshooting section and verification checklist

v1.0.0

  • โœ… Complete brain-inspired intelligence system

  • โœ… Enterprise scalability and user customization

  • โœ… Organized test suite with proper structure

  • โœ… 33 advanced MCP tools fully functional

  • โœ… Multi-language support (6 languages)

  • โœ… 80+ development tools integration

๐Ÿ”ฎ Future Roadmap

  • Visual Interface: Mind map visualization and exploration

  • Team Sharing: Collaborative knowledge base

  • IDE Integrations: VS Code, IntelliJ, Vim plugins

  • Advanced ML: Enhanced neural pattern recognition

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Add tests if applicable

  5. Submit a pull request

License

MIT License - see LICENSE file for details.

Support

  • Report issues on GitHub

  • Check the troubleshooting guide in docs/

  • Review the API documentation for integration details

Available Tools

59 tools
advanced_queryC

Execute advanced Cypher-like graph queries with complex filtering, aggregation, and pattern matching

Inputs: query (required), explain, parameters.

aggregate_queryC

Execute aggregate queries for project insights, statistics, and analytics

Inputs: aggregation (required), limit, filter, group_by, +1 more.

allocate_attentionC

Dynamically allocate attention to specific nodes based on context and cognitive load theory

Inputs: node_ids (required), context, attention_type.

analyze_and_predictC

Trigger immediate pattern analysis and prediction generation based on current project state

Inputs: no named parameters.

analyze_architectureC

Analyze the project architecture and detect design patterns, architectural styles, and structural insights

Inputs: limit, pattern_type, min_confidence.

analyze_call_patternsA

Analyze function call patterns, method invocations, and code relationships within TypeScript/JavaScript files. Creates a comprehensive call graph with complexity metrics, recursion detection, and cross-file relationship mapping.

Inputs: file_paths, min_confidence, include_cross_file.

analyze_configuration_relationshipsC

Analyze configuration file relationships and dependencies across the project. Tracks package.json, tsconfig.json, .env files, and other configuration files to understand project setup and dependencies.

Inputs: config_types, min_confidence, include_recommendations.

analyze_documentC

Analyze a specific document file for structure, links, code relationships, and documentation quality

Inputs: file_path (required).

analyze_error_propagationC

Analyze error handling patterns and exception propagation flows across the codebase. Identifies unhandled errors, error handling coverage, and vulnerable areas for improved error resilience.

Inputs: error_types, min_confidence, severity_filter, include_recommendations.

analyze_polyglot_projectB

Analyze project structure for multi-language patterns, architecture style, and language interoperability

Inputs: detailed_frameworks, include_recommendations.

analyze_project_documentationC

Analyze all documentation files in the project including markdown, restructured text, and configuration files. Provides comprehensive documentation analysis with brain-inspired relationship learning.

Inputs: no named parameters.

analyze_test_coverageA

Analyze test coverage by mapping test files to their corresponding implementation files. Identifies test-to-code relationships through naming patterns, imports, and code references with 95% accuracy target.

Inputs: group_by, min_confidence, include_orphans, include_untested.

clear_cacheB

Clear the query cache to free memory and force fresh results

Inputs: affected_paths.

create_context_windowB

Create a temporal context window for grouping related changes and relationships within a specific time period

Inputs: name (required), valid_time_start (required), description, valid_time_end, +1 more.

create_temporal_snapshotC

Create a temporal snapshot of the current knowledge state for analysis and comparison

Inputs: name.

detect_cross_language_apisA

Detect API endpoints, services, and schemas across all supported languages. Identifies REST APIs, GraphQL schemas, gRPC services, WebSocket endpoints, and WebAssembly modules with framework-specific pattern recognition.

Inputs: api_types, min_confidence, include_schemas.

detect_cross_language_depsC

Detect cross-language dependencies and communication patterns in polyglot projects

Inputs: min_confidence, dependency_types, include_confidence.

detect_enhanced_frameworksC

Comprehensive framework detection across web, mobile, desktop, game, ML/AI, and cloud categories

Inputs: categories, force_refresh, min_confidence.

detect_project_toolingB

Detect available development tools across all languages in the project

Inputs: force_refresh, language_filter.

execute_saved_queryB

Execute a previously saved query template with optional parameter overrides

Inputs: query_id (required), parameters.

generate_multi_language_refactoringsC

Generate intelligent refactoring suggestions for multi-language codebases

Inputs: focus_area, max_effort, include_risks.

get_attention_statsA

Get brain-inspired attention system statistics showing attention allocation, modality distribution, focus efficiency, and cognitive load metrics

Inputs: no named parameters.

get_bi_temporal_statsB

Get bi-temporal knowledge model statistics showing valid time vs transaction time tracking, context windows, and temporal relationship analysis

Inputs: no named parameters.

get_cache_statsA

Get query cache statistics including hit rate, memory usage, and performance metrics

Inputs: no named parameters.

get_contextC

Get contextual information about the current project state and previous interactions

Inputs: context_type (required), limit.

get_context_summaryA

Get current context summary across all hierarchical levels (immediate, session, project, domain) with most relevant context items

Inputs: level.

get_documentation_insightsC

Get intelligent insights about documentation quality, coverage gaps, broken links, and improvement recommendations

Inputs: no named parameters.

get_documentation_statisticsA

Get comprehensive statistics about project documentation including word counts, link analysis, and coverage metrics

Inputs: no named parameters.

get_document_relationshipsA

Get relationships between documentation and code files, including implementation mappings and cross-references

Inputs: no named parameters.

get_emerging_patternsB

Get patterns that are emerging but not yet fully established, with emergence stage and confidence

Inputs: emergence_stage.

get_framework_recommendationsC

Get intelligent recommendations based on detected frameworks and project patterns

Inputs: framework_names, recommendation_type.

get_hebbian_statsA

Get Hebbian learning statistics showing associative connections, co-activation patterns, and neural-inspired relationship strengthening

Inputs: no named parameters.

get_hierarchical_context_statsB

Get hierarchical context system statistics showing multi-level context awareness, context distribution, and brain-inspired context management

Inputs: no named parameters.

get_ignore_statsA

Get statistics about currently active ignore patterns and their effectiveness

Inputs: no named parameters.

get_inhibitory_statsA

Get brain-inspired inhibitory learning statistics including pattern counts, strength distribution, and learning effectiveness

Inputs: no named parameters.

get_insightsC

Generate comprehensive project insights and analytics with actionable recommendations

Inputs: categories, min_confidence, actionable_only.

get_multi_modal_fusion_statsA

Get multi-modal confidence fusion statistics showing evidence combination, modality reliability, and advanced confidence calibration

Inputs: no named parameters.

get_pattern_predictionsB

Get specific pattern predictions with probability, timeframe, and confidence analysis

Inputs: pattern_type.

get_performanceB

Get performance statistics and identify slow operations in the mind map system

Inputs: operation, include_recent, slow_threshold_ms.

get_prediction_engine_statsB

Get pattern prediction engine statistics showing emerging patterns, predictions, and trend analysis

Inputs: no named parameters.

get_statsC

Get statistics about the current mind map and project analysis

Inputs: no named parameters.

get_tooling_recommendationsC

Get intelligent recommendations for missing or beneficial development tools

Inputs: priority_filter, include_install_commands.

init_claude_codeA

Get comprehensive setup instructions and configuration guidance for integrating Mind Map MCP with Claude Code

Inputs: platform, setup_type.

invalidate_relationshipC

Mark a relationship as no longer valid (set valid time end)

Inputs: edge_id (required), reason, evidence, invalidation_date.

predict_errorsC

Analyze code patterns and predict potential errors before they occur based on historical data and code analysis

Inputs: limit, file_path, risk_threshold.

predict_pattern_emergenceC

Predict when a specific pattern will emerge with detailed analysis and alternatives

Inputs: pattern_type (required).

query_bi_temporalC

Query relationships with temporal constraints - valid time, transaction time, and context windows

Inputs: as_of, valid_at, context_window, include_history, +2 more.

query_mindmapB

Query the project mind map with enhanced semantic search, context-aware relevance scoring, and intelligent routing. Supports file path queries, function/class name searches, semantic concept matching, and multi-modal confidence fusion.

Inputs: query (required), type, limit, include_metadata.

run_language_toolC

Execute a specific development tool and return results with issue analysis

Inputs: language (required), tool_name (required), args, timeout.

run_tool_suiteC

Run multiple development tools and aggregate results for comprehensive analysis

Inputs: parallel, fail_fast, languages, tool_types.

save_queryB

Save a query template for reuse with parameters

Inputs: name (required), query (required), description (required), parameters, +1 more.

scan_projectB

Perform a fresh scan of the project to update the mind map with current file structure. Supports multiple project contexts via project_root parameter or MCP_PROJECT_ROOT environment variable.

Inputs: force_rescan, project_root, include_analysis.

suggest_explorationC

Get intelligent suggestions for where to look or what to explore based on a task description

Inputs: task_description (required), current_location, exploration_type.

suggest_fixesA

Get intelligent fix suggestions for errors based on historical data, error patterns, and contextual analysis

Inputs: error_message (required), limit, file_path, error_type, +2 more.

temporal_queryC

Query code evolution over time, track changes, and analyze trends

Inputs: time_range (required), entity, metric, analysis_type.

test_ignore_patternsB

Test ignore patterns against project files to see what would be ignored

Inputs: patterns (required), sample_paths.

update_attentionB

Update attention system from user activity (file access, edits, errors, successes) for dynamic attention learning

Inputs: action_type (required), node_ids, query_text.

update_ignore_patternsC

Update ignore patterns for file scanning with support for .gitignore and .mindmapignore files

Inputs: patterns (required), create_mindmapignore.

update_mindmapB

Update the mind map with new knowledge from completed tasks, errors encountered, or solutions found

Inputs: outcome (required), task_description (required), error_details, files_involved, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    C2.9/5.0

    Scored across 59 tools

    Disambiguation2/5

    Many tools have overlapping purposes, such as multiple analyze_* and get_* tools that target similar aspects (e.g., analyze_project_documentation vs analyze_document, get_insights vs analyze_and_predict). This makes it difficult for an agent to select the correct tool without deep reading.

    Naming Consistency5/5

    All tools follow a consistent snake_case verb_noun pattern (e.g., scan_project, query_mindmap, analyze_architecture). There are no deviations or mixed conventions, making the set highly predictable.

    Tool Count1/5

    With 59 tools, the server is far beyond a well-scoped size of 3-15. The number is excessive for a mind map and project analysis server, likely overwhelming agents and indicating poor feature granularity.

    Completeness3/5

    The tool set covers many aspects of analysis, querying, and brain-inspired features, but lacks basic CRUD operations for mind map entities like nodes and relationships. There are overlapping analysis tools, but core creation/deletion is missing, leading to moderate coverage.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that transforms codebases into intelligent, queryable knowledge bases, enabling AI assistants to perform semantic search, explore architecture, and analyze code relationships.
      166
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that gives AI agents structured code understanding and precise code intelligence via local indexing of AST, call graphs, and semantic search.
      73 npm
      4
      Apache 2.0
    • -
      license
      Not graded
      quality
      Not graded
      maintenance
      An advanced MCP server that provides deep code understanding and analysis using GraphRAG, AST parsing, and semantic memory, enabling AI agents to query and interact with complex codebases.
      -