Local-first MCP server for AI-powered codebase intelligence — AST analysis, dependency graphs, and semantic search. Your source code never leaves your machine.
Local-first MCP server for CodeAtlas — AST analysis, codebase intelligence, semantic memory, and A2A orchestration.
2026-11-14
ดาว
—
เครื่องมือ
—
อัปไทม์
—
📌 What is CodeAtlas MCP Server?
A Model Context Protocol (MCP) server that provides:
AST Analysis: Parse TypeScript, Python, PHP, and more.
Dependency Graphs: Visualize call chains and module relationships.
Semantic Search: Find code by meaning, not just syntax.
Local-First: Your code stays on your machine; no telemetry by default.
Cloud Optional: Connect to codeatlas-platform for dream memory, genome immune system, and skills sync.
Why Use It?
Use Case
Benefit
AI IDE Integration
Claude Desktop, Cursor, VSCode — get context-aware code intelligence.
Codebase Audits
Automate dependency analysis, security scans, and refactoring insights.
Semantic Search
Find functions, classes, or modules by intent, not just name.
Multi-Language Support
Works with TypeScript, Python, PHP, and more via AST parsers.
Optional: connect to codeatlas-platform for dreams/genome
🔧 Quick Start
1. Install
# Clone the repo
git clone https://github.com/giauphan/codeatlas-mcp-server.git
cd codeatlas-mcp-server
# Install dependencies (requires Node.js 20+)
pnpm install
2. Configure
# Copy the optional local environment template. This file is ignored by Git.
cp .env.example .env
# Edit .env
# Cloud features require both variables; no default URL is used
# Set CODEATLAS_API_URL to your CodeAtlas API base URL
# Set CODEATLAS_API_KEY to your CodeAtlas API key
3. Build
pnpm run build
4. Run
# Local-only mode (no cloud)
pnpm start
# With cloud connection (requires codeatlas-platform running)
CODEATLAS_API_URL=http://localhost:8080 CODEATLAS_API_KEY=your_api_key_here pnpm start
Zed has no Claude-style hooks, so the Second Brain hooks are exposed as MCP tools instead.
For Claude hook setup, safe diagnostics, rollback controls, and the explicit memory_bootstrap tool for hosts without injection hooks, see Memory pipeline operations.
Option A — automatic setup:
codeatlas-enterprise setup zed
This writes a codeatlas entry into Zed's context_servers (passing CODEATLAS_API_KEY/CODEATLAS_API_URL from your environment). Restart Zed afterward.
Option B — manual: add to Zed settings.json (open via zed: open settings file):
Then in Zed's Agent Panel, call the brain_context tool at the start of a task to inject Second Brain memory, and save_dream_memory after a task to persist learnings. route_task suggests a model/effort (advisory only — Zed does not auto-switch models). See Zed Integration.
🔒 Security & Environment Variables
CodeAtlas MCP Server is designed with a local-first architecture and several security hardening measures to protect your credentials and codebase data:
Credential Storage: Set CODEATLAS_API_KEY in the process environment to avoid storing it in a file. If you configure it in .env or an MCP client setting, the key is stored on disk; protect that file and keep it out of version control.
Strict Destination Validation: When connecting to cloud features, the destination AI and backend URLs are strictly validated. Credentials can only flow to trusted official domains (*.codeatlas.ai, opencode.ai) or local addresses (localhost, 127.0.0.1).
Telemetry & Logging: Potential credential leaks are sanitized and redacted from all console and error logs.
Required & Optional Environment Variables
Variable
Description
Default
CODEATLAS_API_KEY
Secret key to connect to CodeAtlas Cloud services for AI memory and scan features.
(none)
CODEATLAS_API_URL
Target URL for CodeAtlas Cloud. Validated via allowlists to prevent credential exfiltration.
(none)
CODEATLAS_ALLOW_CUSTOM_URL
Set to true to allow sending credentials to self-hosted or unlisted destinations. Required for private network deployments.
false
CODEATLAS_SCAN_AI_KEY
Key for deep AI security scanning using an external LLM.
Oracle DB Required for Persistent Memory: Local-only mode works without Oracle, but dream memory persistence requires it.
Cloud Dream Query Filters: When querying memories with scope, tags, or memory_type filters, the backend performs vector hybrid search on the query text plus SQL filtering on the other parameters. The tags parameter is passed as a JSON string to the upstream API. The related_ids parameter is also supported for filtering by related memory IDs.
Multi-Tenant Not Supported: Only single-tenant mode available.
Security: No built-in rate limiting; use a reverse proxy (Nginx) in production.
