✨ Key Features

• Zero-Cost Local Critic: Offload heavy code review iterations to your local GPU via LM Studio without spending cloud tokens.

• Sub-Millisecond AST Sentinel: Catches syntax errors and dangerous runtime calls (eval, exec, os.system, subprocess) before wasting GPU cycles.

• Deterministic Contract: Enforces structured outputs (APPROVED vs REJECTED with specific line feedback) so the agent automatically refactors code without human intervention.

• Dual Data Sink (DPO Flywheel):

  • SQLite (audit_history.db): Tracks duration, categories, and metrics.

  • Per-Audit JSON (audit_logs/): Stores individual audit records to easily build DPO / Fine-tuning datasets from paired rejected/approved attempts.

Related MCP server: tar-engine

🚀 Quick Start

1. Prerequisites

• Python 3.10+

• LM Studio running an OpenAI-compatible Local Server (http://localhost:1234/v1)

• Antigravity or any MCP-compatible client

2. Installation

# Clone the repository
git clone [https://github.com/xTanThaix/mcp-local-auditor.git](https://github.com/xTanThaix/mcp-local-auditor.git)
cd mcp-local-auditor

# Set up virtual environment
python -m venv .venv

# Activate virtual environment
# On Windows:
.venv\Scripts\activate
# On macOS/Linux:
source .venv/bin/activate

# Install dependencies
pip install -r requirements.txt

3. Register MCP Server

Open your Antigravity MCP config file:

• Windows: %USERPROFILE%\.gemini\config\mcp_config.json

• macOS / Linux: ~/.gemini/config/mcp_config.json

Add the server definition inside mcpServers:

{
  "mcpServers": {
    "lmstudio-auditor": {
      "command": "D:\\Hucdeline\\.venv\\Scripts\\python.exe",
      "args": ["D:\\Hucdeline\\auditor_bridge.py"]
    }
  }
}

Note: Replace D:\\Hucdeline with your actual project directory path.

4. Configure LM Studio

1. Open LM Studio and load any instruction-tuned coding model (e.g., Qwen-2.5-Coder, DeepSeek-Coder, Llama-3).

2. Go to the Local Server (Developer) tab.

3. Set Port to ...(e.g.,1234) and click Start Server.

🤖 Agent Loop Setup (Custom Rule / Skill)

Add the following rule to your Antigravity Agent (mcp-studio-loop):

# Mandatory MCP Code Audit Protocol
Every time code is generated or refactored, you MUST invoke the `audit_submission` tool:
- Arguments: `task_goal`, `output_content`, `strict_rules`
- If STATUS == "REJECTED": Read `ACTIONABLE_FEEDBACK`, refactor the code, and re-submit.
- If STATUS == "APPROVED": Output the final solution to the user.
- Maximum retry limit: 5 attempts before breaking loop.

4. Configure LM Studio Open LM Studio and load any instruction-tuned coding model (e.g., Qwen-2.5-Coder, DeepSeek-Coder, Llama-3).

Go to the Local Server tab.

Set Port to xxxx and click Start Server.

🤖 Agent Loop Setup (Custom Rule / Skill) Add the following rule to your Antigravity Agent (mcp-studio-loop):

Markdown

Mandatory MCP Code Audit Protocol

Every time code is generated or refactored, you MUST invoke the audit_submission tool:

• Arguments: task_goal, output_content, strict_rules

• If STATUS == "REJECTED": Read ACTIONABLE_FEEDBACK, refactor the code, and re-submit.

• If STATUS == "APPROVED": Output the final solution to the user.

• Maximum retry limit: 5 attempts before breaking loop. 🧪 Testing Run the included Pytest suite to verify AST checks, SQLite migrations, and mock responses:

Bash pytest test_auditor.py -v

📸 Real-World Audit in Action (Example Usage / Usage Example)

Here is an example of MCP Local Auditor rejecting an unoptimized code path with actionable feedback, prompting the coding agent to self-heal and re-verify: Example Usage: After the tests pass, audit each modified file one by one using the "lmstudio-auditor" tool.

💖 Support & Donations If this project saved you API costs and helped streamline your local LLM workflow, consider supporting development:

Ko-fi: https://ko-fi.com/xtanthaix

GitHub Sponsors: Click the Sponsor button on this repository

📄 License MIT License. Free for open-source and commercial use.