┌─────────────────────────────────────────────────────────────┐
│                      VS Code Copilot                        │
│           (Asks questions about your codebase)              │
└────────────────────────┬────────────────────────────────────┘
                         │ MCP Protocol
                         ▼
┌─────────────────────────────────────────────────────────────┐
│                  CodeGraph MCP Server                       │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────────┐  │
│  │ search_code  │  │ get_call_    │  │ get_related_     │  │
│  │ (semantic)   │  │ graph        │  │ files            │  │
│  └──────────────┘  └──────────────┘  └──────────────────┘  │
└────────────────────────┬────────────────────────────────────┘
                         │
                         ▼
          ┌──────────────────────────────┐
          │    SQLite Database           │
          │  .repo-index/index.db        │
          ├──────────────────────────────┤
          │ Graph: Nodes + Edges         │
          │  - Classes, Methods          │
          │  - Calls, Implements         │
          │  - Injects, Registers        │
          ├──────────────────────────────┤
          │ Vectors: Code Chunks         │
          │  - Method-level embeddings   │
          │  - Semantic similarity       │
          └──────────────────────────────┘
                         │
                    (Optional)
                         ▼
          ┌──────────────────────────────┐
          │      Neo4j (Visualization)   │
          │   Graph queries & exploration│
          └──────────────────────────────┘

cd /path/to/codegraph-mcp
npm install

# Install Ollama from https://ollama.ai
# Pull embedding model
ollama pull qwen3-embedding

# Set environment variables
export EMBEDDING_ENDPOINT="http://localhost:11434/api/embeddings"
export EMBEDDING_MODEL="qwen3-embedding"

export EMBEDDING_ENDPOINT="https://<your-instance>.openai.azure.com/openai/deployments/<model>/embeddings?api-version=2024-02-01"
export EMBEDDING_API_KEY="your-api-key"
export EMBEDDING_MODEL="text-embedding-ada-002"  # or text-embedding-3-small

cd /path/to/your/repo
GRAPH_ONLY=true node /path/to/codegraph-mcp/src/indexer.js

cd /path/to/your/repo
EMBEDDING_ENDPOINT="http://localhost:11434/api/embeddings" \
EMBEDDING_MODEL="qwen3-embedding" \
node /path/to/codegraph-mcp/src/indexer.js

cd /path/to/your/repo
mkdir -p .vscode
cp /path/to/codegraph-mcp/.vscode-mcp-example.json .vscode/mcp.json

{
  "servers": {
    "repo-index": {
      "command": "node",
      "args": ["/absolute/path/to/codegraph-mcp/src/mcpServer.js"]
    }
  }
}

{
  "servers": {
    "repo-index": {
      "command": "node",
      "args": ["/absolute/path/to/codegraph-mcp/src/mcpServer.js"],
      "env": {
        "EMBEDDING_ENDPOINT": "http://localhost:11434/api/embeddings",
        "EMBEDDING_MODEL": "qwen3-embedding"
      }
    }
  }
}

Cmd+Shift+P → "Developer: Reload Window"

⚠️  search_code is unavailable: Index was built in GRAPH-ONLY mode (no embeddings).

To enable semantic search:
1. Re-run the indexer WITHOUT GRAPH_ONLY=true
2. Set EMBEDDING_ENDPOINT and EMBEDDING_MODEL environment variables
3. Indexing will take ~2-2.5 hours for embeddings

Graph-based tools (get_call_graph, get_related_files) are still available.

Find JWT token validation logic
Show me retry mechanisms
Where is error handling implemented?
Find code that calculates profit margins

What's the blast radius for AuthenticationHelper?
Show me what depends on MarginController
What does UserService call?
Find all callers of ValidateToken method

What files are related to Program.cs?
Show me files connected to this service

What's the impact of changing the authorization middleware?
Find all implementations of IRepository pattern
Show me error handling across the codebase

Use get_call_graph to analyze the blast radius of AuthHelper with depth 3
Use search_code to find margin calculation patterns

# Day 1: Quick exploration with graph-only
cd ~/projects/new-codebase
GRAPH_ONLY=true node ~/tools/codegraph-mcp/src/indexer.js

# Use graph tools in VS Code Copilot
# "Use get_call_graph to show what depends on AuthHelper"

# Export to Neo4j for visual exploration
NEO4J_PASSWORD="password" node ~/tools/codegraph-mcp/export-to-neo4j.js .

# Day 2: Add semantic search after initial exploration
EMBEDDING_ENDPOINT="http://localhost:11434/api/embeddings" \
EMBEDDING_MODEL="qwen3-embedding" \
node ~/tools/codegraph-mcp/src/indexer.js

# Now use semantic search
# "Use search_code to find JWT validation logic"

# Pull and run Neo4j
docker run -d \
  --name neo4j-codegraph \
  -p 7474:7474 -p 7687:7687 \
  -e NEO4J_AUTH=neo4j/password \
  neo4j:latest

# Check status
docker ps | grep neo4j-codegraph

docker stop neo4j-codegraph
docker start neo4j-codegraph

cd /path/to/your/repo
NEO4J_PASSWORD="password" \
node /path/to/codegraph-mcp/export-to-neo4j.js .

// View all classes
MATCH (n:Class) RETURN n LIMIT 50

// Find call chains
MATCH path=(a:Method)-[:CALLS*1..3]->(b:Method)
RETURN path LIMIT 25

// DI registrations (interface → implementation)
MATCH (i:Interface)<-[:REGISTERS]-(impl)
RETURN i, impl

// Dead code (no incoming references)
MATCH (n:Method)
WHERE NOT ()-[:CALLS]->(n)
RETURN n.name, n.path

// Blast radius from a specific method
MATCH path=(caller)-[:CALLS*1..3]->(target:Method {name: 'Authenticate'})
RETURN path

-- Count nodes by type
SELECT kind, COUNT(*)
FROM nodes
GROUP BY kind;

-- Count edges by type
SELECT kind, COUNT(*)
FROM edges
GROUP BY kind;

-- Find methods with most callers
SELECT n.name, n.path, COUNT(e.src_id) as caller_count
FROM nodes n
JOIN edges e ON e.dst_id = n.id AND e.kind = 'calls'
WHERE n.kind = 'method'
GROUP BY n.id
ORDER BY caller_count DESC
LIMIT 20;

-- Find classes with no callers (potential dead code)
SELECT n.name, n.path
FROM nodes n
WHERE n.kind = 'class'
  AND NOT EXISTS (
    SELECT 1 FROM edges e WHERE e.dst_id = n.id
  );

-- View embedding statistics
SELECT
  COUNT(*) as total_chunks,
  AVG(LENGTH(text)) as avg_chunk_size,
  SUM(LENGTH(embedding)) / COUNT(*) as avg_embedding_size
FROM chunks;

cd /path/to/your/repo
GRAPH_ONLY=true /path/to/codegraph-mcp/nightly-refresh.sh

cd /path/to/your/repo
/path/to/codegraph-mcp/nightly-refresh.sh

crontab -e
# Add line (runs daily at 2 AM):
0 2 * * * /path/to/your/repo/nightly-refresh-index.sh >> /path/to/your/repo/.repo-index/refresh.log 2>&1

codegraph-mcp/
├── schema.sql                # Database schema (graph + vectors)
├── SCHEMA.md                  # Design rationale
├── src/
│   ├── db.js                  # SQLite connection
│   ├── indexer.js             # Main indexing engine
│   ├── graph.js               # Call graph queries
│   ├── search.js              # Vector similarity search
│   ├── embeddings.js          # Embedding provider abstraction
│   ├── mcpServer.js           # MCP protocol server
│   └── extractors/
│       ├── csharp.js          # C# symbol extraction
│       ├── angular.js         # TypeScript/Angular extraction
│       └── yaml.js            # YAML pipeline extraction
├── export-to-neo4j.js         # Neo4j export utility
├── nightly-refresh.sh         # Incremental update script
└── .vscode-mcp-example.json   # MCP config template

const hash = sha256(chunk.text);
const existing = db.prepare(
  `SELECT id FROM chunks WHERE node_id = ? AND content_hash = ?`
).get(chunk.nodeId, hash);
if (!existing) {
  chunksToEmbed.push({ ...chunk, hash });
}

const diff = getChangedFiles(lastCommit);
targets = diff.filter(d => EXT_LANG[path.extname(d.filePath)]);

# Check Ollama is running
curl http://localhost:11434/api/tags

# Verify model is installed
ollama list

# Re-pull if needed
ollama pull qwen3-embedding

# Check if Neo4j container is running
docker ps | grep neo4j

# View Neo4j logs
docker logs neo4j-codegraph

# Restart Neo4j
docker restart neo4j-codegraph

# Remove and recreate (clears data!)
docker rm -f neo4j-codegraph
docker run -d \
  --name neo4j-codegraph \
  -p 7474:7474 -p 7687:7687 \
  -e NEO4J_AUTH=neo4j/password \
  neo4j:latest