Stores and queries code graph representations with vector indexing, enabling graph traversal, relationship analysis, and semantic search across parsed TypeScript/NestJS codebases.
Provides deep understanding of NestJS architectural patterns including controllers, services, modules, dependency injection, HTTP endpoints, guards, pipes, and interceptors.
Generates embeddings for semantic code search, powers natural language to Cypher query conversion, and enables vector-based similarity matching for code discovery.
Parses TypeScript projects using AST analysis to extract code entities, relationships, and framework patterns for graph-based code understanding.
Click on "Install 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 Graph Contextfind all services that depend on the UserRepository"
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 Graph Context
Give your AI coding assistant a photographic memory of your codebase.
Code Graph Context is an MCP server that builds a semantic graph of your TypeScript codebase, enabling Claude to understand not just individual files, but how your entire system fits together.
Config-Driven & Extensible: Define custom framework schemas to capture domain-specific patterns beyond the included NestJS support. The parser is fully configurable to recognize your architectural patterns, decorators, and relationships.
┌─────────────────────────────────────────────────────────────┐
│ YOUR CODEBASE │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ Service │ │Controller│ │ Module │ │ Entity │ │
│ └────┬─────┘ └────┬─────┘ └────┬─────┘ └────┬─────┘ │
└───────┼─────────────┼─────────────┼─────────────┼──────────┘
│ │ │ │
▼ ▼ ▼ ▼
┌─────────────────────────────────────────────────────────────┐
│ CODE GRAPH CONTEXT │
│ │
│ AST Parser ──► Neo4j Graph ──► Vector Embeddings │
│ (ts-morph) (Relationships) (Local or OpenAI) │
│ │
└─────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐
│ CLAUDE CODE │
│ │
│ "What services depend on UserService?" │
│ "What's the blast radius if I change this function?" │
│ "Find all HTTP endpoints that accept a UserDTO" │
│ "Refactor this across all 47 files that use it" │
│ │
└─────────────────────────────────────────────────────────────┘Why Code Graph Context?
Without Code Graph | With Code Graph |
Claude reads files one at a time | Claude understands the entire dependency tree |
"What uses this?" requires manual searching | Instant impact analysis with risk scoring |
Refactoring misses edge cases | Graph traversal finds every reference |
Large codebases overwhelm context | Semantic search finds exactly what's relevant |
Multi-file changes are error-prone | Swarm agents coordinate parallel changes |
Features
Multi-Project Support: Parse and query multiple projects in a single database with complete isolation
Semantic Search: Vector-based search using local or OpenAI embeddings to find relevant code
Natural Language Querying: Convert questions into Cypher queries
Framework-Aware: Built-in NestJS schema with ability to define custom framework patterns
Weighted Graph Traversal: Intelligent traversal scoring paths by importance and relevance
Workspace Support: Auto-detects Nx, Turborepo, pnpm, Yarn, and npm workspaces
Parallel & Async Parsing: Multi-threaded parsing with Worker threads for large codebases
Streaming Import: Chunked processing for projects with 100+ files
Incremental Parsing: Only reparse changed files
File Watching: Real-time graph updates on file changes
Impact Analysis: Assess refactoring risk (LOW/MEDIUM/HIGH/CRITICAL)
Dead Code Detection: Find unreferenced exports with confidence scoring
Duplicate Detection: Structural (AST hash) and semantic (embedding similarity) duplicates
Swarm Coordination: Multi-agent stigmergic coordination with pheromone decay
Architecture
TypeScript Source → AST Parser (ts-morph) → Neo4j Graph + Vector Embeddings → MCP ToolsCore Components:
src/core/parsers/typescript-parser.ts- AST parsing with ts-morphsrc/storage/neo4j/neo4j.service.ts- Graph storage and queriessrc/core/embeddings/embeddings.service.ts- Embedding service (local sidecar or OpenAI)src/mcp/mcp.server.ts- MCP server and tool registration
Dual-Schema System:
Core Schema: AST-level nodes (ClassDeclaration, MethodDeclaration, ImportDeclaration, etc.)
Framework Schema: Semantic interpretation (NestController, NestService, HttpEndpoint, etc.)
Nodes have both coreType (AST) and semanticType (framework meaning), enabling queries like "find all controllers" while maintaining AST precision.
Quick Start
Prerequisites
Node.js >= 18
Python >= 3.10 (for local embeddings)
Docker (for Neo4j)
No API keys required. Local embeddings work out of the box using a Python sidecar.
1. Install
npm install -g code-graph-context
code-graph-context init # Sets up Neo4j + Python sidecar + downloads embedding modelThe init command handles everything:
Starts a Neo4j container via Docker
Creates a Python virtual environment
Installs embedding dependencies (PyTorch, sentence-transformers)
Downloads the default embedding model (~3GB)
2. Configure Claude Code
claude mcp add --scope user code-graph-context -- code-graph-contextThat's it. No API keys needed. Restart Claude Code and you're ready to go.
Want to use OpenAI instead? See Embedding Configuration below.
3. Parse Your Project
In Claude Code, say:
"Parse this project and build the code graph"
Claude will run parse_typescript_project and index your codebase.
Configuration Files
Claude Code stores MCP server configs in JSON files. The location depends on scope:
Scope | File | Use Case |
User (global) |
| Available in all projects |
Project |
| Project-specific config |
Local |
| Git-ignored local overrides |
Manual Configuration
If you prefer to edit the config files directly:
~/.claude.json (user scope - recommended):
{
"mcpServers": {
"code-graph-context": {
"command": "code-graph-context"
}
}
}With OpenAI (optional):
{
"mcpServers": {
"code-graph-context": {
"command": "code-graph-context",
"env": {
"OPENAI_ENABLED": "true",
"OPENAI_API_KEY": "sk-your-key-here"
}
}
}
}From source installation:
{
"mcpServers": {
"code-graph-context": {
"command": "node",
"args": ["/absolute/path/to/code-graph-context/dist/cli/cli.js"]
}
}
}Environment Variables
Variable | Required | Default | Description |
| No |
| Neo4j connection URI |
| No |
| Neo4j username |
| No |
| Neo4j password |
| No |
| Local embedding model (see Embedding Configuration) |
| No |
| Texts per embedding batch (lower = less memory, higher = faster) |
| No |
| Port for local embedding server |
| No | auto ( | Device for embeddings. Auto-detects MPS on Apple Silicon |
| No |
| Set |
| No |
| Set |
| No* | - | Required when |
Core Capabilities
Semantic Code Search
Find code by describing what you need, not by memorizing file paths:
"Find where user authentication tokens are validated"
"Show me the database connection pooling logic"
"What handles webhook signature verification?"Impact Analysis
Before you refactor, understand the blast radius:
┌─────────────────────────────────────────────────────────────┐
│ Impact Analysis: UserService.findById() │
├─────────────────────────────────────────────────────────────┤
│ Risk Level: HIGH │
│ │
│ Direct Dependents (12): │
│ └── AuthController.login() │
│ └── ProfileController.getProfile() │
│ └── AdminService.getUserDetails() │
│ └── ... 9 more │
│ │
│ Transitive Dependents (34): │
│ └── 8 controllers, 15 services, 11 tests │
│ │
│ Affected Files: 23 │
│ Recommendation: Add deprecation warning before changing │
└─────────────────────────────────────────────────────────────┘Graph Traversal
Explore relationships in any direction:
UserController
│
├── INJECTS ──► UserService
│ │
│ ├── INJECTS ──► UserRepository
│ │ │
│ │ └── MANAGES ──► User (Entity)
│ │
│ └── INJECTS ──► CacheService
│
└── EXPOSES ──► POST /users
│
└── ACCEPTS ──► CreateUserDTODead Code Detection
Find code that can be safely removed:
Dead Code Analysis: 47 items found
├── HIGH confidence (23): Exported but never imported
│ └── formatLegacyDate() in src/utils/date.ts:45
│ └── UserV1DTO in src/dto/legacy/user.dto.ts:12
│ └── ... 21 more
├── MEDIUM confidence (18): Private, never called
└── LOW confidence (6): May be used dynamicallyDuplicate Code Detection
Identify DRY violations across your codebase:
Duplicate Groups Found: 8
Group 1 (Structural - 100% identical):
├── validateEmail() in src/auth/validation.ts:23
└── validateEmail() in src/user/validation.ts:45
Recommendation: Extract to shared utils
Group 2 (Semantic - 94% similar):
├── parseUserInput() in src/api/parser.ts:78
└── sanitizeInput() in src/webhook/parser.ts:34
Recommendation: Review for consolidationSwarm Coordination
Execute complex, multi-file changes with parallel AI agents.
The swarm system enables multiple Claude agents to work on your codebase simultaneously, coordinating through the code graph without stepping on each other.
┌──────────────────┐
│ ORCHESTRATOR │
│ │
│ "Add JSDoc to │
│ all services" │
└────────┬─────────┘
│
┌─────────────┼─────────────┐
│ │ │
▼ ▼ ▼
┌──────────┐ ┌──────────┐ ┌──────────┐
│ Worker 1 │ │ Worker 2 │ │ Worker 3 │
│ │ │ │ │ │
│ Claiming │ │ Working │ │ Claiming │
│ AuthSvc │ │ UserSvc │ │ PaySvc │
└──────────┘ └──────────┘ └──────────┘
│ │ │
└─────────────┼─────────────┘
│
▼
┌─────────────────────────────┐
│ PHEROMONE TRAILS │
│ │
│ AuthService: [claimed] │
│ UserService: [modifying] │
│ PayService: [claimed] │
│ CacheService: [available] │
│ │
└─────────────────────────────┘Two Coordination Mechanisms
1. Pheromone System (Stigmergic)
Agents leave markers on code nodes that decay over time—like ants leaving scent trails:
Pheromone | Half-Life | Meaning |
| 2 min | "I'm looking at this" |
| 1 hour | "This is my territory" |
| 10 min | "I'm actively changing this" |
| 24 hours | "I finished work here" |
| Never | "Don't touch this" |
| 5 min | "I'm stuck" |
Self-healing: If an agent crashes, its pheromones decay and the work becomes available again.
2. Task Queue (Blackboard)
Explicit task management with dependencies:
┌─────────────────────────────────────────────────────────────┐
│ TASK QUEUE │
├─────────────────────────────────────────────────────────────┤
│ [available] Add JSDoc to UserService priority: high │
│ [claimed] Add JSDoc to AuthService agent: worker1 │
│ [blocked] Update API docs ─────────────────► depends on ──┤
│ [in_progress] Add JSDoc to PaymentService agent: worker2 │
│ [completed] Add JSDoc to CacheService ✓ │
└─────────────────────────────────────────────────────────────┘Swarm Tools
Tool | Purpose |
| Add a task to the queue |
| Query tasks with filters |
| Claim/start/release a task |
| Complete/fail/request review |
| Leave a marker on a code node |
| Query what other agents are doing |
| Remove pheromones after completion |
Example: Parallel Refactoring
// Orchestrator decomposes the task and creates individual work items
swarm_post_task({
projectId: "backend",
swarmId: "swarm_rename_user",
title: "Update UserService.findUserById",
description: "Rename getUserById to findUserById in UserService",
type: "refactor",
createdBy: "orchestrator"
})
// Workers claim and execute tasks
swarm_claim_task({ projectId: "backend", swarmId: "swarm_rename_user", agentId: "worker_1" })
// ... do work ...
swarm_complete_task({ taskId: "task_1", agentId: "worker_1", action: "complete", summary: "Renamed method" })Install the Swarm Skill
For optimal swarm execution, install the included Claude Code skill that teaches agents the coordination protocol:
# Copy to your global skills directory
mkdir -p ~/.claude/skills
cp -r skills/swarm ~/.claude/skills/Or for a specific project:
cp -r skills/swarm .claude/skills/The skill provides:
Worker agent protocol with step-by-step workflow
Multi-phase orchestration patterns (discovery, contracts, implementation, validation)
Common failure modes and how to prevent them
Complete tool reference
Once installed, just say "swarm" or "parallel agents" and Claude will use the skill automatically.
See skills/swarm/SKILL.md for the full documentation.
All Tools
Tool | Description |
Discovery | |
| List parsed projects in the database |
| Semantic search using vector embeddings |
| Explore relationships from a node |
| Convert questions to Cypher queries |
Analysis | |
| Assess refactoring risk (LOW/MEDIUM/HIGH/CRITICAL) |
| Find unreferenced exports and methods |
| Find structural and semantic duplicates |
Parsing | |
| Build the graph from source |
| Monitor async parsing jobs |
| Auto-update graph on file changes |
| Stop file watching |
| List active file watchers |
Swarm | |
| Add task to the queue |
| Query tasks |
| Claim/start/release tasks |
| Complete/fail/review tasks |
| Leave coordination markers |
| Query what others are doing |
| Clean up after swarm completion |
Utility | |
| Verify database connectivity |
Tool Workflow Patterns
Pattern 1: Discovery → Focus → Deep Dive
list_projects → search_codebase → traverse_from_node → traverse (with skip for pagination)Pattern 2: Pre-Refactoring Safety
search_codebase("function to change") → impact_analysis(nodeId) → review risk levelPattern 3: Code Health Audit
detect_dead_code → detect_duplicate_code → prioritize cleanupPattern 4: Multi-Agent Work
swarm_post_task → swarm_claim_task → swarm_complete_task → swarm_get_tasks(includeStats) → swarm_cleanupMulti-Project Support
All query tools require projectId for isolation. You can use:
Project ID:
proj_a1b2c3d4e5f6(auto-generated)Project name:
my-backend(from package.json)Project path:
/path/to/project(resolved automatically)
// These all work:
search_codebase({ projectId: "my-backend", query: "auth" })
search_codebase({ projectId: "proj_a1b2c3d4e5f6", query: "auth" })
search_codebase({ projectId: "/path/to/my-backend", query: "auth" })Framework Support
NestJS (Built-in)
Deep understanding of NestJS patterns:
Controllers with route analysis (
@Controller,@Get,@Post, etc.)Services with dependency injection mapping (
@Injectable)Modules with import/export relationships (
@Module)Guards, Pipes, Interceptors as middleware chains
DTOs with validation decorators (
@IsString,@IsEmail, etc.)Entities with TypeORM relationship mapping
NestJS-Specific Relationships:
INJECTS- Dependency injectionEXPOSES- Controller exposes HTTP endpointMODULE_IMPORTS,MODULE_PROVIDES,MODULE_EXPORTS- Module systemGUARDED_BY,TRANSFORMED_BY,INTERCEPTED_BY- Middleware
Custom Framework Schemas
The parser is config-driven. Define your own framework patterns:
// Example: Custom React schema
const REACT_SCHEMA = {
name: 'react',
decoratorPatterns: [
{ pattern: /^use[A-Z]/, semanticType: 'ReactHook' },
{ pattern: /^with[A-Z]/, semanticType: 'HOC' },
],
nodeTypes: [
{ coreType: 'FunctionDeclaration', condition: (node) => node.name?.endsWith('Provider'), semanticType: 'ContextProvider' },
],
relationships: [
{ type: 'PROVIDES_CONTEXT', from: 'ContextProvider', to: 'ReactHook' },
]
};The dual-schema system means every node has:
coreType: AST-level (ClassDeclaration, FunctionDeclaration)semanticType: Framework meaning (NestController, ReactHook)
This enables queries like "find all hooks that use context" while maintaining AST precision for refactoring.
Embedding Configuration
Local embeddings are the default — no API key needed. The Python sidecar starts automatically on first use and runs a local model for high-quality code embeddings.
The sidecar uses MPS (Apple Silicon GPU) when available, falling back to CPU. It auto-shuts down after 3 minutes of inactivity to free memory, and restarts lazily when needed (~15-20s).
Device override: Set
EMBEDDING_DEVICE=cputo force CPU if MPS causes issues.Half precision: Set
EMBEDDING_HALF_PRECISION=trueto load the model in float16, roughly halving memory usage.
Available Models
Set via the EMBEDDING_MODEL environment variable:
Model | Dimensions | RAM (fp16) | Quality | Best For |
| 1024 | ~700 MB | Best | Default, code-specific encoder, fast |
| 1536 | ~4.5 GB | Great | Machines with 32+ GB RAM |
| 768 | ~250 MB | Good | General purpose, low RAM |
| 384 | ~100 MB | OK | Minimal RAM, fast |
| 768 | ~300 MB | Good | Code + prose mixed |
| 768 | ~250 MB | Good | Balanced quality/speed |
| 384 | ~65 MB | OK | Smallest footprint |
Example: Use a lightweight model on a low-memory machine:
claude mcp add --scope user code-graph-context \
-e EMBEDDING_MODEL=BAAI/bge-base-en-v1.5 \
-- code-graph-contextSwitching Models
Switching models requires re-parsing — vector index dimensions are locked per model. Drop existing indexes first:
DROP INDEX embedded_nodes_idx IF EXISTS;
DROP INDEX session_notes_idx IF EXISTS;Then re-parse your project with the new model configured.
Using OpenAI Instead
If you prefer OpenAI embeddings (higher quality, requires API key):
claude mcp add --scope user code-graph-context \
-e OPENAI_ENABLED=true \
-e OPENAI_API_KEY=sk-your-key-here \
-- code-graph-contextTroubleshooting
MCP Server Not Connecting
# Check the server is registered
claude mcp list
# Verify Neo4j is running
docker ps | grep neo4j
# Test manually
code-graph-context statusEmbedding Errors
"Failed to generate embedding" — The local sidecar may not have started. Check:
# Verify Python deps are installed
code-graph-context status
# Re-run init to fix sidecar setup
code-graph-context initOut of memory (large model on 16GB machine) — Switch to a lighter model:
claude mcp add --scope user code-graph-context \
-e EMBEDDING_MODEL=BAAI/bge-base-en-v1.5 \
-- code-graph-contextUsing OpenAI and getting auth errors — Ensure your key is configured:
claude mcp remove code-graph-context
claude mcp add --scope user code-graph-context \
-e OPENAI_ENABLED=true \
-e OPENAI_API_KEY=sk-your-key-here \
-- code-graph-contextNeo4j Memory Issues
For large codebases, increase memory limits:
# Stop and recreate with more memory
code-graph-context stop
code-graph-context init --memory 4GParsing Timeouts
Use async mode for large projects:
parse_typescript_project({
projectPath: "/path/to/project",
tsconfigPath: "/path/to/project/tsconfig.json",
async: true // Returns immediately, poll with check_parse_status
})CLI Commands
code-graph-context init [options] # Set up Neo4j + Python sidecar + embedding model
code-graph-context status # Check Docker/Neo4j/sidecar status
code-graph-context stop # Stop Neo4j containerInit options:
-p, --port <port>- Bolt port (default: 7687)--http-port <port>- Browser port (default: 7474)--password <password>- Neo4j password (default: PASSWORD)-m, --memory <size>- Heap memory (default: 2G)-f, --force- Recreate container
Contributing
git clone https://github.com/drewdrewH/code-graph-context.git
cd code-graph-context
npm install
npm run build
npm run dev # Watch modeConventional Commits: feat|fix|docs|refactor(scope): description
License
MIT - see LICENSE