VibeBridge
Click on "Deploy 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., "@VibeBridgeSearch my workspace for all TODO comments and show me where they are"
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.
VibeBridge
A secure local bridge between Gemini Spark and your development workspace.
Give an AI agent controlled access to your files, codebase, and terminal without handing it unrestricted access to your machine.
Overview
VibeBridge is a local runtime and desktop interface that exposes a developer's selected workspace to Gemini Spark through the Model Context Protocol (MCP).
Think of it as a controlled execution layer:
Gemini Spark handles reasoning and decides which tools it needs.
VibeBridge performs those actions locally.
The security layer keeps file operations inside the selected workspace.
The permission layer lets the user control writes and command execution.
VibeBridge is not an LLM or agent framework. It is the local bridge that gives an external AI agent access to a real development environment.
Related MCP server: lnwjud
Why VibeBridge?
AI coding tools are most useful when they can actually work with a project: inspect files, search a codebase, modify source files, and run commands.
The problem is trust. Giving an AI unrestricted access to a computer is a bad security boundary.
VibeBridge is designed around a narrower model:
Expose one workspace, provide explicit tools, enforce a filesystem boundary, and keep sensitive actions behind permissions.
What it provides
Capability | What VibeBridge does |
π Workspace access | Restricts filesystem operations to the selected project directory |
π Code search | Lets the agent search files and inspect relevant source code |
βοΈ File editing | Supports safe exact-match edits instead of blind overwrites |
π₯οΈ Command execution | Runs development commands with the workspace as the working directory |
π Permission controls | Separates read, write, and execute operations |
π MCP over HTTPS | Exposes the MCP server through a configurable tunnel |
π₯οΈ Desktop UI | Provides workspace selection, endpoint information, activity logs, and permission dialogs |
Architecture
flowchart LR
A[Gemini Spark] <-->|MCP / HTTPS| B[Public Tunnel]
B <--> C[VibeBridge Runtime]
C --> D[MCP Server]
C --> E[Permission Manager]
C --> F[Security Sandbox]
C --> G[Activity Logger]
F --> H[Filesystem Tools]
F --> I[Terminal Executor]
H --> J[(Selected Workspace)]
I --> JThe main packages are separated by responsibility:
VibeBridge
βββ apps/
β βββ desktop/ # React + TypeScript + Tauri desktop UI
βββ packages/
β βββ mcp-server/ # MCP transport, server, tools and tunnel handling
β βββ security/ # Workspace sandbox and permission policy
β βββ shared/ # Shared types, schemas and contracts
βββ tests/ # Security, permission and integration testsRequest flow
Gemini Spark connects to VibeBridge through the MCP endpoint.
VibeBridge validates the requested tool and its arguments.
Filesystem paths are resolved against the selected workspace.
Sensitive write/execute operations are passed through the permission policy.
The tool executes locally and returns a structured MCP response.
Activity is logged by the runtime.
Security Model
Security is one of the core design goals of VibeBridge.
Workspace sandbox
File operations are resolved against the canonical workspace path rather than relying on string-prefix checks. This is intended to prevent common traversal and symlink-escape scenarios.
Permission tiers
Tier | Tools | Typical policy |
Read |
| Can be auto-approved |
Write |
| User approval recommended |
Execute |
| User approval recommended |
Available permission modes are:
promptβ ask before writes and command executionauto_approve_readβ automatically allow reads, prompt for writes and executionauto_approve_allβ automatically allow all actionsdeny_writesβ read-only mode; reject writes and commands
Safer file editing
edit_file works with an exact old_text match. If the expected text is not found, the edit fails instead of silently modifying the wrong location.
Command limits
Command execution uses the selected workspace as cwd, supports configurable timeouts, and caps command output to reduce the impact of runaway processes or extremely large logs.
Important: VibeBridge is a security boundary, not a guarantee that arbitrary AI-generated commands are safe. Review your tunnel configuration, permission mode, and commands before enabling broad access.
MCP Tools
VibeBridge currently exposes eight tools:
Tool | Purpose |
| List files and directories in the workspace |
| Read text files, optionally by line range |
| Search the workspace using text or regex |
| Create a new file |
| Replace an exact text match in an existing file |
| Delete a file or directory |
| Move or rename a file or directory |
| Execute a shell command from the workspace |
Quick Start
Prerequisites
Node.js 18+
npm 9+
ngrok account and auth token when using the ngrok tunnel
Rust and Cargo when building/running the native Tauri shell
1. Clone
git clone https://github.com/assishmoncs/vibebridge.git
cd vibebridge2. Install dependencies
npm install3. Configure the environment
cp .env.example .envA minimal configuration looks like:
PORT=3000
HOST=127.0.0.1
VIBEBRIDGE_WORKSPACE=/absolute/path/to/your/project
ENABLE_TUNNEL=true
TUNNEL_PROVIDER=ngrok
NGROK_AUTHTOKEN=your_ngrok_auth_token
PERMISSION_MODE=prompt4. Build the project
npm run build5. Run VibeBridge
For the desktop development UI:
npm run dev:desktopFor the server/runtime:
npm startOr run the Tauri desktop shell:
npm run tauri devOnce the runtime is running, use the MCP endpoint shown by VibeBridge to connect Gemini Spark.
Tunnel Configuration
VibeBridge supports a pluggable tunnel configuration through environment variables.
ngrok
ENABLE_TUNNEL=true
TUNNEL_PROVIDER=ngrok
NGROK_AUTHTOKEN=your_ngrok_auth_tokenVibeBridge can then expose the local MCP server through an HTTPS endpoint suitable for a remote client.
Direct mode
The environment configuration also supports a direct tunnel provider when the surrounding network setup already provides the required connectivity.
Development
Useful commands
Command | Purpose |
| Install workspace dependencies |
| Build all workspace packages |
| Run the test suite |
| Start the desktop frontend in development mode |
| Start the MCP server workspace |
| Start the built MCP server |
| Run the native Tauri desktop app |
Testing
npm testThe repository includes tests for permission handling, filesystem/security behavior, editing, command execution, and MCP-related integration behavior.
Project Status
VibeBridge is currently at v0.1.0 and is actively evolving.
Implemented
Streamable HTTP MCP transport
Workspace-scoped filesystem sandbox
Canonical path / symlink escape checks
Exact-match file editing
Command execution with timeout and output limits
Permission management for read, write, and execute operations
React + Tauri desktop interface
Configurable HTTPS tunnel provider
Planned
Visual Git diff inspection
Cloudflare Quick Tunnel support
Workspace indexing and symbol search
Further desktop UX improvements
Contributing
Contributions are welcome.
A good starting point is to keep changes focused within the existing package boundaries:
apps/desktopfor the UIpackages/mcp-serverfor MCP/runtime behaviorpackages/securityfor sandboxing and permission logicpackages/sharedfor shared contracts and schemas
Before opening a pull request, run:
npm test
npm run buildLicense
VibeBridge is released under the MIT License.
VibeBridge β controlled local execution for AI-powered development.
This server cannot be deployed
Maintenance
Related MCP Connectors
Connect AI agents to Filepad workspaces through OAuth MCP.
Manage files and folders directly from your workspace. Read and write files, list directories, creβ¦
The OpenZeppelin Solidity Contracts MCP server integrates OpenZeppelin's security and style rules into AI-driven development workflows, enabling AI assistants to generate safe, correct, and production-ready smart contracts. It automatically validates generated code against OpenZeppelin standards (including imports, modifiers, naming conventions, and security checks) and supports various contract types including ERC-20, ERC-721, ERC-1155, Stablecoins, RWA, Governor, and Account contracts through prompt-driven workflows.
Generate contextual prompts and reusable agent skills, evaluate prompts with the 16-dimension Prompt Score, and manage saved work in PromptDrive. Twelve MCP tools also provide authorized access to private Memory for source-grounded answers. Connect over Streamable HTTP using OAuth 2.1 and PKCE. Generation consumes account quota and automatically saves successful results; Memory access follows account permissions and plan limits.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceA local MCP server that enables Gemini Spark to safely access and work with files in a user-selected workspace via authenticated HTTPS tunnel, with sandboxing, policy enforcement, and audit logging.3-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to securely access local development capabilities such as files, Git, processes, browser control, Windows automation, WSL, and observability through MCP on Windows and macOS.MIT
- FlicenseNot gradedqualityBmaintenanceEnables Gemini Spark to securely connect via full OAuth 2.1 and use 30+ terminal, file, web, Git, and system management tools through MCP.-
- AlicenseNot gradedqualityBmaintenanceEnables ChatGPT to read and edit local project files, inspect Git changes, and run approved development scripts through a secure MCP tunnel, with optional Codex Desktop integration.177 npm2Apache 2.0