Nexus

mcp
Security Audit
Fail
Health Pass
  • License — License: AGPL-3.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 419 GitHub stars
Code Fail
  • execSync — Synchronous shell command execution in apps/bridge/src/browser-portal.ts
  • spawnSync — Synchronous process spawning in apps/bridge/src/browser-portal.ts
  • fs.rmSync — Destructive file system operation in apps/bridge/src/browser-portal.ts
  • process.env — Environment variable access in apps/bridge/src/browser-portal.ts
  • network request — Outbound network request in apps/bridge/src/browser-portal.ts
  • network request — Outbound network request in apps/bridge/src/generic-mcp/generic-mcp-client.ts
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Connect web AI assistants to local files, terminals, Git, and desktop tools through MCP, with user-controlled permissions.

README.md

Nexus

Nexus Mascot

Dedicated Local AI Control Plane for ChatGPT, DeepSeek & Modern Web AI Assistants
Powered by the LocalBridge 332 Canonical MCP Tool Architecture & Durable Action Ledger

English | 简体中文

Version 1.3.2 332 MCP Tools License AGPL-3.0 Platforms Tests


1. Overview

Nexus is an enterprise-grade Local AI Control Plane designed specifically for ChatGPT, DeepSeek, and modern AI coding assistants. It securely bridges remote LLMs to your local workstation through a high-performance Secure MCP Tunnel (Streamable HTTP / SSE with OAuth 2.0 & Bearer tokens).

Nexus allows AI agents to inspect, edit, build, debug, and orchestrate complex local engineering workflows within strictly enforced sandbox boundaries—without exposing your full filesystem or transmitting proprietary code to untrusted cloud intermediaries.

 ChatGPT / DeepSeek / Web AI Assistants
               │
               │ Secure MCP Tunnel (Streamable HTTP / SSE, Bearer lb_xxx, OAuth 2.0)
               ▼
┌────────────────────────────────────────────────────────────────────────┐
│                   Nexus Desktop Control Center (Tauri 2)               │
│                                                                        │
│  Fastify MCP & REST API Server (Port 18080)   SQLite Persistence (WAL) │
└──────────────────────────────────┬─────────────────────────────────────┘
                                   │ Bidirectional JSON-RPC 2.0 (WebSocket)
                                   ▼
┌────────────────────────────────────────────────────────────────────────┐
│                   Nexus Local Runner Daemon                            │
│                                                                        │
│  ├── 332 Canonical MCP Tools Across 24 Capabilities                    │
│  ├── Action Ledger WAL (Crash Recovery & Idempotent Replay)            │
│  ├── Native Windows Computer Use (WinRT OCR, UI Automation)            │
│  ├── Sandboxed Workspaces & Managed Git Worktrees                      │
│  ├── Persistent Development Runtimes & Windows Job Objects             │
│  ├── Language Server Protocol (LSP - TypeScript / Python)              │
│  ├── Headless & Interactive Browser Automation Engine                  │
│  └── Local Intelligence Store (Memory, Rules, Knowledge, Prompts)      │
└────────────────────────────────────────────────────────────────────────┘

2. Desktop Control Center Showcase

The Nexus Desktop Control Center provides developers with real-time observability, granular security governance, and seamless tool management across all connected AI agents.

Nexus Desktop Overview

Nexus Desktop Control Center: Real-time system telemetry, active workspaces, registered tools, and CPU/memory metrics.


Project Authorizations & Sandboxing

Multi-Tier Security & Project Sandboxing
Granular read/write permissions, path isolation, and AST command risk controls.

Skills Hub & Zero-Bloat Execution

Skills Hub & Hot-Reload Engine
Zero-bloat modular tool orchestration with instant hot-reloading.

Secure MCP Tunnel Service

Secure MCP Tunnel & OAuth 2.0
Streamable HTTP/SSE tunnel with DPAPI encrypted credential vault.

Managed MCP Processes & API Ecosystem

Managed MCP Process Ecosystem
Figma, GitHub, SQLite, Filesystem & dynamic agent runtimes.


3. Generative & Procedural 3D Automation (Blender)

Nexus seamlessly bridges generative AI models directly into Blender 4.x / 5.x, enabling end-to-end procedural 3D modeling, geometry node orchestration, PBR procedural shader synthesis, and photorealistic asset generation directly from high-level conversational prompts.

Stylized Cartoon Cottage - Procedural Render

Autonomous 3D Scene Generation: Stylized Cartoon Cottage featuring procedural masonry, wooden framing, roof shingles, and atmospheric lighting.


Blender Quad Topology & Wireframe

Production-Grade Clean Quad Topology
Optimized edge flow, non-destructive modifiers, and game-ready mesh density.

Blender Steampunk Bottle Generator

Procedural Hard-Surface & PBR Shading
Steampunk brass apparatus with real-time procedural glass and liquid shaders.


4. Unity GameDev In-Editor AI Copilot

Transform your game development pipeline with the Nexus Unity Copilot. Operating directly inside the Unity Editor via bidirectional JSON-RPC MCP bridges, AI agents can construct scenes, author custom HLSL/Shader Graph shaders, configure physics, and validate gameplay logic in real time.

Unity Deep Space Black Hole Scene

Nexus In-Editor Copilot: Real-time generation of the gravitational lensing accretion disk and deep space photon ring.


Custom Shader Properties & AI Game Developer Tab

AI Game Developer Tab & Custom Shaders
Interactive shader parameter tuning and in-editor inspector integration.

Unity Viewport & Gameplay Real-Time Simulation

Scene Hierarchy & Real-Time Simulation
Automated GameObject hierarchy construction, skybox configuration, and camera positioning.


5. Core Capabilities & Architectural Highlights

1. 332 Canonical MCP Tools

  • Single Source of Truth: All 332 tools are formally defined in @localbridge/protocol, with strict input schemas, risk ratings, and automated evidence tracking.
  • Zero Hallucination Guarantee: Covers 24 capability dimensions: Filesystem, Advanced FS, Git Operations, Command Execution, Persistent Background Jobs, LSP Code Intelligence, Managed Worktrees, Browser Automation, Windows Computer Use, Vision Analysis, Document Engineering, Local Intelligence (Memory/Rules/Knowledge), Agent Orchestration, and System Discovery.

2. ACID-Compliant Action Ledger WAL

  • Write-Ahead Logging: Every critical tool execution is recorded in a write-ahead log (.wal) prior to side-effect application.
  • Crash Recovery & State Replay: Automatically recovers pending operations and restores consistent workspace states after host reboot or runner crashes.
  • Idempotency Guard: Eliminates duplicate execution and resource waste during intermittent network reconnections.

3. Native Windows Computer Use & Vision

  • Semantic UI Locating: Combines WinRT Native OCR and UI Accessibility trees to locate screen elements without relying on fragile pixel coordinates.
  • Multi-Monitor Control: Window switching, foregrounding, mouse tracking, drag-and-drop, and keystroke dispatching with non-bypassable human takeover controls.
  • Visual Validation: Screenshot capture, image comparison, and difference inspection for automated UI testing.

4. Durable Execution & Process Isolation

  • Windows Job Objects: Enforces hard process hierarchy isolation, CPU quotas, and memory caps on spawned commands.
  • Terminal Daemon (node-pty): Stateful pseudo-terminal sessions with ANSI log streaming and exit code tracking.
  • Command Risk Engine: AST-based command classification (SAFE, CAUTION, DANGEROUS) that blocks destructive system calls (rm -rf /, format, reg delete) by default.

5. Local Intelligence Store

  • Vectorless & Vector Hybrid: SQLite-backed fast exact-match and semantic retrieval for persistent project memory, team rules, knowledge documentation, and custom prompt templates.
  • Context Compactor: Automatic token reduction and conversational compaction for extended multi-turn agent tasks.
  • Extensible Skills Engine: Declarative deterministic workflows with dynamic candidate proposal, automated validation, and live hot-reloading.

6. Multi-Tier Path Sandbox & Enterprise Security

  • Physical Canonical Containment: Enforces containment inside authorized project roots via fs.realpathSync.native to eliminate directory traversal (../) and prefix-confusion attacks.
  • Symlink & Junction Escape Shield: Blocks malicious symlinks and Windows NTFS directory junctions pointing outside project boundaries.
  • Dual Token Cryptographic Isolation: MCP client tokens (lb_...) and Runner daemon tokens (lbr_...) are generated with 256-bit entropy and stored exclusively as SHA-256 hashes. Timing side-channel attacks are mitigated via crypto.timingSafeEqual.
  • Sensitive File Shield: Automatically masks .env*, *.pem, *.key, id_rsa, .git, and cloud credentials.

6. Monorepo Project Layout

Nexus/
├── apps/
│   ├── desktop/          # Tauri 2 + React + Vite Desktop Control Center
│   ├── runner/           # Local execution daemon (332 tools, Action Ledger, Computer Use)
│   ├── server/           # Fastify MCP Server with SQLite WAL persistence & REST API
│   └── bridge/           # Standalone Nexus MCP Bridge (OAuth 2.0 / ChatGPT / DeepSeek)
├── packages/
│   ├── protocol/         # Pure protocol types, 332 Canonical tool definitions, RPC schemas
│   ├── security/         # Sandboxing, path verification, and command risk engine
│   └── shared/           # Structured logger (Pino), config loader, crypto utilities
├── tests/                # Comprehensive test suites (190+ suites, 1200+ tests)
├── docs/                 # Architectural specifications, security models, and guides
├── artifacts/            # Production truth evidence, capability matrices, and audit ledgers
└── scripts/              # Build automation, bundling tools, and release scripts

7. Quick Start

Option A: Desktop Installer (Recommended)

  1. Open the v1.3.2 release page and download the installer package for your operating system:
    • Windows (x64 Installer): Nexus_1.3.2_x64-setup.exe
    • macOS (Universal DMG): Nexus_1.3.2_universal.dmg
    • macOS (Apple Silicon DMG): Nexus_1.3.2_aarch64.dmg
    • Linux (Debian/Ubuntu .deb): Nexus_1.3.2_amd64.deb
    • Linux (Universal .AppImage): Nexus_1.3.2_amd64.AppImage
    • Browser Userscript (Tampermonkey): nexus-web-agent.user.js
  2. Run the installer. Nexus launches in your system tray with bundled Node.js runtime, language servers, and background runner daemon ready out of the box.

Option B: Build & Run from Source

Prerequisites: Node.js >= 24, pnpm >= 10, Rust stable.

# 1. Clone the repository
git clone https://github.com/ysunyang4/Nexus.git
cd Nexus

# 2. Install workspace dependencies
pnpm install

# 3. Build core packages and applications
pnpm run build

# 4. Launch Desktop Control Center
pnpm --filter @localbridge/desktop dev

8. Connecting AI Clients

Step 1: Authorize a Local Project

  1. Open Nexus Desktop Control Center.
  2. Under Workspace -> Projects, click Authorize Project and select your directory (e.g., D:\projects\my-app).
  3. Set Access Mode (read-only or read-write) and Execution Mode (disabled, safe-only, or project-code)—both can be dynamically switched at any time without restarting.

Step 2: Generate an MCP Client Token

  1. Go to Settings -> Tokens.
  2. Click Generate Token, choose MCP Client Token (lb_...), and copy the displayed token.

Step 3: Configure Your AI Client

ChatGPT / Custom GPT Actions:
Add the Streamable HTTP endpoint:

http://127.0.0.1:18080/mcp

Header: Authorization: Bearer lb_your_token_here

Standard MCP Client Configuration (mcp_config.json / Client Settings):

{
  "mcpServers": {
    "nexus": {
      "url": "http://127.0.0.1:18080/mcp",
      "headers": {
        "Authorization": "Bearer lb_your_token_here",
        "MCP-Protocol-Version": "2024-11-05"
      }
    }
  }
}

Cursor / Windsurf / Any MCP Client:

  • Transport: Streamable HTTP or SSE
  • URL: http://127.0.0.1:18080/mcp
  • Headers: {"Authorization": "Bearer lb_your_token_here"}

9. Official Communities & Developer Contact

Join our community for developer discussions, feature requests, live bug reports, and updates:

Official Communities

Official Communities
QQ Group: 1131916140
Telegram Group: @YSUN_WEBAI

Developer Contact

Direct Developer Contact
WeChat: (In-App QR)
Telegram / WhatsApp / LINE


10. Sponsor & Support

If Nexus has helped your workflow, research, or daily development, consider buying the author a coffee ☕!

Your generous support helps sustain active open-source maintenance, feature evolution, and bug fixes.

WeChat Pay (微信支付)

WeChat Pay (微信支付)
Alipay (支付宝)

Alipay (支付宝)

11. Development & Quality Verification

# Typecheck across all 7 workspace packages (0 errors)
pnpm run typecheck

# Build all packages, bundles, and Tauri resources
pnpm run build

# Run the test suite
pnpm run test

# Run Rust desktop check
cargo check --manifest-path apps/desktop/src-tauri/Cargo.toml

12. License, Anti-Rebranding & Security Disclaimer

  • Software license (GNU AGPL-3.0): Nexus v1.3.2 is distributed under the GNU Affero General Public License v3.0 (AGPL-3.0-only), which permits personal and commercial use, modification and redistribution subject to its terms.
    • When source obligations apply: Distributing covered works (including modified binaries), and allowing users to interact over a network with a modified version, can trigger the license's corresponding-source and notice requirements. Private modifications not conveyed or offered as a modified network service are not automatically required to be publicly published. Refer to the actual AGPL-3.0 license, especially Sections 4–6 and 13, for the precise scope.
    • Attribution and accurate origin: Preserve copyright, license and other legal notices as the AGPL requires, indicate relevant changes, and do not falsely represent modified builds as official releases. The AGPL's termination and reinstatement provisions are governed by Section 8; this README does not add an automatic-termination rule.
    • Branding: The software license does not automatically grant trademark rights or permission to imply official endorsement. See Brand Guidelines. These guidelines do not override AGPL-granted software freedoms.
    • Third-party notices: See THIRD_PARTY_NOTICES.md for dependencies and a separate architecture-reference acknowledgement.
  • Security & Unrestricted Mode Disclaimer (SECURITY.md):
    • By default, Nexus enforces strict path sandboxing (read-only) and AST command risk filtering (safe-only).
    • If you explicitly enable read-write, project-code, Computer Use UI automation, or Unrestricted / Full-Control Mode, you assume full responsibility for all commands executed and files modified by connected AI models. Always back up critical work or use Git version control.

Reviews (0)

No results found