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., "@Verdict MCP Submit auth_handler.py for audit"
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.
AI agents suffer from Context Drift, Illusion of Completion, and Quality Degradation:
❌ Mark tasks DONE but leave empty pass statements
❌ Skip critical error handling
❌ Generate unstyled "developer art" UIs
❌ Write superficial tests with no real assertions
❌ No accountability — human must review everything manuallyRelated MCP server: Deslopify
Verdict is a programmatic gatekeeper that sits between the AI agent and your codebase. Every task must pass all three gates before being marked complete:
pip install verdict-mcp
# OR from source:
git clone https://github.com/Zubair-z/VERDICT-MCP.git
cd VERDICT-MCP
pip install -r requirements.txtverdict init myproject
cd myprojectThis creates: plan.md + auth_handler.py + db_handler.py + tests/test_auth_handler.py
python -m verdict_mcppython -m verdict_mcp.api_server
# → http://localhost:8000
curl http://localhost:8000/healthcurl -X POST http://localhost:8000/pipeline/run \
-H "Content-Type: application/json" \
-d '{
"task_id": "TASK_001",
"source_files": ["auth_handler.py"],
"test_file": "tests/test_auth_handler.py",
"target_file": "auth_handler.py",
"ui_file": "main_window.py"
}'graph LR
A[AI Agent] -->|MCP / HTTP| B{Verdict}
B --> C[AST Auditor]
B --> D[UI Enforcer]
B --> E[Test Runner]
C --> F[pass/TODO/err/docstring checks]
D --> G[glassmorphism/neon/layout]
E --> H[pytest + coverage + mutation]
F & G & H --> I{TASK COMPLETED?}
I -->|Yes| J[Git Snapshot]
I -->|No| AMethod | Path | Description |
|
| Server health |
|
| Initialize plan |
|
| Get task states |
|
| Task details |
|
| AST audit files |
|
| Design tokens |
|
| Validate UI |
|
| Coverage + mutation |
|
| Coverage report |
|
| Full lifecycle |
Language | Extensions | Checks Applied |
Python |
| Full AST audit (pass, TODO, try-except, docstrings) |
JavaScript |
| TODO, empty functions, missing try-catch |
TypeScript |
| TODO, empty functions, missing try-catch |
React |
| TODO, empty components, missing error handling |
Go |
| TODO, empty funcs, missing error handling |
Rust |
| TODO, empty fn, missing error handling |
Java |
| TODO, empty methods, missing try-catch |
Kotlin |
| TODO, empty fun, missing error handling |
# Scaffold a new project
verdict init myproject
# Run Verdict checks on current project
verdict verify
# Start MCP server
python -m verdict_mcp
# Start REST API
python -m verdict_mcp.api_server
# Run tests locally
python -m pytest tests/ -v --cov=verdict_mcp --cov-report=term-missing# Start REST API
docker-compose up verdict-mcp
# Start MCP stdio mode
docker-compose up verdict-mcp-stdioCopy .vscode-extension/ folder to ~/.vscode/extensions/verdict-mcp/
Restart VS Code
Open a Python file → press Ctrl+Shift+V
Or enable auto-audit on save in settings
We welcome contributions! See CONTRIBUTING.md for guidelines.
This server cannot be deployed
MCP server for Mint — AI-powered QA that runs your app in a real browser on every PR.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
A paid remote MCP for AI agent browser approval MCP, built to return verdicts, receipts, usage logs,
