A Model Context Protocol (MCP) server that provides intelligent code analysis and context retrieval for AI coding assistants.

License: MIT Node.js Version

Code Intelligence MCP Server enhances AI coding assistants with deep codebase understanding through:

• Semantic Search: Find code by meaning, not just keywords
• Graph-RAG: Context-aware code retrieval using knowledge graphs
• Call Chain Analysis: Trace function dependencies and impacts
• Smart Context: Automatically inject relevant code snippets into AI conversations

Perfect for use with Claude Code, Cline, or any MCP-compatible AI assistant.

Via npm (recommended):

npm install -g @ozbombor/code-intelligence-mcp

Via git:

git clone https://github.com/Darkbluelr/code-intelligence-mcp.git
cd code-intelligence-mcp
./install.sh

• Node.js >= 18.0.0
• Bash shell
• ripgrep (optional, for faster search)
• jq (optional, for JSON processing)

As MCP Server (recommended):

Add to your MCP client configuration:

{
 "mcpServers": {
 "code-intelligence": {
 "command": "code-intelligence-mcp",
 "args": []
 }
 }
}

Command Line:

ci-search "find authentication code"
ci-search --help

# Natural language queries
ci-search "how does user authentication work"

# Get relevant context with smart pruning
ci_graph_rag --query "fix login bug" --budget 8000

# Trace function dependencies
ci_call_chain --symbol "handleLogin" --depth 3

# Analyze change impact
ci_impact --file "src/auth.ts"

# Intelligent bug locator
ci_bug_locate --error "TypeError: Cannot read property 'user'"

20+ tools available - Each tool supports --help for detailed usage.

The server supports multiple embedding providers with automatic fallback:

Three-tier Fallback Strategy:

1. Ollama (Local, Free) → Preferred, no network latency, privacy-safe
2. OpenAI API (Cloud, Paid) → Automatic fallback when Ollama unavailable
3. Keyword Search → Final fallback when no embedding service available

Installation:

# Install Ollama
curl -fsSL https://ollama.com/install.sh | sh
# Pull the embedding model
ollama pull nomic-embed-text

Configuration:

# .devbooks/config.yaml
embedding:
 provider: ollama # or 'auto' for automatic detection
 ollama:
 model: nomic-embed-text
 endpoint: http://localhost:11434
 timeout: 30

Usage:

# Build the embedding index
ci-search build
# Search with Ollama
ci-search "authentication code"

Setup:

# Set your API key
export OPENAI_API_KEY="sk-..."

Configuration:

# .devbooks/config.yaml
embedding:
 provider: openai
 openai:
 model: text-embedding-3-small
 api_key: ${OPENAI_API_KEY} # or set directly
 base_url: https://api.openai.com/v1
 timeout: 30

Usage:

# Build index with OpenAI
ci-search build
# Or force OpenAI for a single search
ci-search "user authentication" --provider openai

Keyword search works out of the box without any configuration:

# Force keyword search
ci-search "error handling" --provider keyword

Automatic Provider Detection:

# .devbooks/config.yaml
embedding:
 provider: auto # Tries Ollama → OpenAI → Keyword
 fallback_to_keyword: true
 auto_build: true

Command-line Override:

# Override provider for a single search
ci-search "test" --provider ollama --ollama-model mxbai-embed-large
# JSON output with custom settings
ci-search "payment" --format json --top-k 10 --threshold 0.7

Environment Variables:

• OPENAI_API_KEY - OpenAI API key
• EMBEDDING_API_KEY - Generic embedding API key
• PROJECT_ROOT - Project root directory

All features degrade gracefully:

• No embeddings? Falls back to keyword search
• No SCIP index? Uses regex parsing
• No external tools? Core features still work
• No git history? Hotspot analysis disabled

This means you can start using the MCP server immediately without any configuration.

For advanced usage, see the local documentation:

• Complete tool reference and examples
• Architecture and system design
• Performance tuning guide
• Troubleshooting tips

Run ./install.sh to access full documentation locally.

Enable automatic context injection for Claude Code:

ci-setup-hook

This installs a hook that automatically injects relevant code context when you interact with Claude, making your AI assistant more aware of your codebase without manual queries.

# Search with specific mode
ci-search "user service" --mode semantic --limit 5
# Trace call chains
ci_call_chain --symbol "processPayment" --direction both
# Check architecture
ci_arch_check --path src/

Run comprehensive demos with A/B comparison:

# Run quick comparison demo
bash demo/00-quick-compare.sh
# Run all demos
bash demo/run-suite.sh
# Compare versions (if available)
bash demo/compare.sh baseline.json current.json

The demo suite showcases:

• Automatic context injection vs manual queries
• Semantic search and Graph-RAG capabilities
• Performance benchmarks and metrics
• A/B comparison between different configurations

Metrics are generated by python3 benchmarks/run_benchmarks.py into benchmark_result.json. Use python3 benchmarks/update_readme.py to refresh this section.

Updated at: 2026年01月24日T06:27:38+00:00

Contributions welcome! Please read CONTRIBUTING.md first.

MIT License - see LICENSE file for details.

Built with: Model Context Protocol, tree-sitter, SCIP

Need help? Open an issue on your repo or check docs/TECHNICAL.md.