CodeAtlas Platform MCP server
Commit Nov 13, 2026Provides an AI-powered codebase intelligence backend with AST analysis, knowledge graphs, and semantic memory for advanced code analysis.
Also known as giauphan/codeatlas-platform
- Stars
- 12
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 13, 2026
- License
- MIT
What is CodeAtlas Platform MCP?
CodeAtlas Platform provides an AI-powered codebase intelligence backend with AST analysis, knowledge graphs, and semantic memory for advanced code analysis.
Summary generated from the project's README
About CodeAtlas Platform MCP server
CodeAtlas Platform provides a foundation for building AI-native code analysis services. It functions as an MCP server that offers over 30 tools for deep codebase intelligence, including AST analysis for TypeScript, Python, and JavaScript. Developers can connect via stdio for Claude Desktop or use SSE transport for Cursor and VSCode. The system manages complex data through a knowledge graph and semantic memory using SQLite with sqlite-vec for vector search.
This platform is designed for developers needing multi-tenant infrastructure with built-in security and documentation capabilities. It requires a Firebase service account for authentication and an NVIDIA NIM API key to enable vector search via embeddings. The architecture supports advanced features like automated architecture documentation through DeepWiki and enterprise vulnerability scanning. Users can manage projects and API keys through a React and Vite management dashboard.
What you can do with it
- 1Semantic code searchQuery codebase information using vector search capabilities powered by NVIDIA embeddings.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
CODEATLAS_API_KEY
| Name | Description | |
|---|---|---|
| CODEATLAS_API_KEY | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablegiauphan/codeatlas-platform is public and reachablegithub.com/giauphan/codeatlas-platform ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/giauphan/codeatlas-platform ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubCodeAtlas Platform
AI-powered codebase intelligence platform — MCP Server, AST analysis, Knowledge Graph, and semantic memory with SQLite + sqlite-vec as the default database.
Ship a secure, multi-tenant codebase intelligence backend without rebuilding authentication, MCP tooling, semantic memory, and knowledge graph infrastructure from scratch. CodeAtlas Platform is an open-source foundation for developers who want a clear starting point for AI-native code analysis services.
[!IMPORTANT] This repository is a foundation, not a substitute for a threat model. Review Known limitations and adapt the defaults to your infrastructure before serving production traffic.
Why this platform?
| Concern | Included foundation |
|---|---|
| MCP Server | 30+ tools via stdio or SSE transport (Claude, Cursor, VSCode) |
| Semantic memory | Dream memory store with SQLite + sqlite-vec vector search |
| Knowledge graph | Genome DNA + immune system patterns, consolidation engine |
| Multi-tenant | Tenant isolation via authStorage.run + Firebase auth |
| AST analysis | TypeScript/Python/JS parsing via @typescript-eslint/typescript-estree and py-ast |
| DeepWiki | Multi-provider LLM (Anthropic/OpenAI/Ollama) automated architecture documentation with Q&A |
| Security scanner | Enterprise vulnerability scanning built-in |
| A2A protocol | Agent-to-agent orchestration with registry |
| Dashboard | React + Vite management UI for API keys and projects |
Architecture
AI IDE (Claude/Cursor) → MCP (stdio/SSE) → Platform :3381 → SQLite + sqlite-vec + Firebase + NVIDIA
| Layer | Components |
|---|---|
| Presentation | Express HTTP, MCP SSE, A2A Agent Protocol, REST API |
| Services | Dream Memory, Genome DNA, Second Brain, Consolidation Engine, Security Scanner |
| Data | SQLite + sqlite-vec (PostgreSQL optional), Firebase Firestore, NVIDIA NIM embeddings |
Architecture diagrams
| Diagram | File |
|---|---|
| System architecture | diagrams/system.mmd |
| Second Brain flow | diagrams/second-brain.mmd |
| Dream lifecycle | diagrams/dreams.mmd |
| Genome + Immune system | diagrams/genome.mmd |
| MCP architecture | architecture/mcp.md |
| Deployment | diagrams/deployment.mmd |
| A2A + Sync | diagrams/a2a-sync.mmd |
Quick start
Requirements
- Node.js 20+
- pnpm 9+ (
corepack enable && corepack prepare pnpm@9 --activate) - SQLite +
sqlite-vec(bundled — no external database server required) - Firebase service account (for multi-tenant auth)
- NVIDIA NIM API key (for embeddings)
1. Clone and install
git clone https://github.com/giauphan/codeatlas-platform.git
cd codeatlas-platform
pnpm install
2. Configure environment
cp .env.example .env
# Edit .env with your Firebase and NVIDIA credentials
See docs/CONFIGURATION.md or docs/DEVELOPMENT.md for the full env var reference.
3. Build
pnpm run build
4. Initialize database
pnpm run db-init
5. Start the server
# Production mode (SSE on :3381)
PORT=3381 pnpm start
# Development mode (hot reload)
pnpm run dev
# Stdio mode (for Claude Desktop — leave PORT unset)
pnpm start
Server runs at http://localhost:3381. Health check: GET /health.
MCP integration
Claude Desktop (stdio)
Add to claude_desktop_config.json:
{
"mcpServers": {
"codeatlas": {
"command": "npx",
"args": ["-y", "codeatlas-ai"],
"env": {
"CODEATLAS_API_KEY": "your_api_key"
}
}
}
}
Cursor / VSCode (SSE)
{
"mcpServers": {
"codeatlas": {
"url": "http://localhost:3381/sse"
}
}
}
See docs/API_EXAMPLES.md for full curl flows and transport modes.
MCP tools (30+)
| Category | Tools |
|---|---|
| Dreams | save_dream_memory, query_dream_memories, sync_dreams |
| Genome | search_genome, save_genome, scan_immune |
| Skills | search_skills, get_skill, install_skill |
| Scanner | scan_enterprise_vulnerabilities |
| Code | code_search, search_files, read_file |
| Projects | list_projects, get_project_structure, get_dependencies |
| Architecture | generate_system_flow, generate_feature_flow_diagram, trace_feature_flow |
| DeepWiki | deepwiki_generate, deepwiki_get_tree, deepwiki_get_page, deepwiki_query |
Full tool reference: docs/architecture/mcp.md.
Documentation
| Guide | Purpose |
|---|---|
| Development | Local dev setup, env vars, troubleshooting |
| Deployment | PM2, systemd, Nginx TLS reverse proxy |
| DeepWiki | LLM config, Markdown docs, architecture generation |
| API examples | curl flows, MCP configs, REST endpoints |
| Architecture overview | Layers, services, integrations |
| MCP architecture | Tool registration, transports, request flow |
| Memory pipeline runbook | Capture, acknowledgement, extraction, recovery, retention, and rollout checks |
| Memory pipeline results | Verification evidence, quality measurements, and remaining release gates |
| Quick setup | Legacy condensed guide |
Known limitations
- SQLite dependency: Data lives in a local SQLite file (default
./data/codeatlas.db) withsqlite-vecfor vector search. Postgres is available as an opt-in backend. - Firebase auth: Multi-tenant mode requires Firebase Admin SDK + service account. API-key-only mode supported for single-tenant.
- NVIDIA embeddings: Vector search depends on NVIDIA NIM API. Without
NVIDIA_API_KEY, queries fall back to date-ordered results. - Local indexing: Pure cloud deployments cannot index local code — run the
codeatlas-aiclient locally to sync AST data. - Dashboard: Management UI ships separately in
dashboard/— build and deploy independently.
See CHANGELOG.md for release history.
Contributing
Bug reports, documentation fixes, tests, and focused feature contributions are welcome. Start with CONTRIBUTING.md, then look for issues labeled good first issue or help wanted.
For security vulnerabilities, follow SECURITY.md instead of opening a public issue.
License
Distributed under the MIT License. Maintained by @giauphan.
CodeAtlas Platform MCP questions
Does it support multi-tenancy?
Yes, it supports multi-tenant isolation using Firebase authentication.
What programming languages can it analyze?
The platform performs AST analysis for TypeScript, Python, and JavaScript.