approval-gate
MCP server that provides human-in-the-loop approval for risky AI agent actions, with durable state and audit logs.
README
<div align="center">
approval-gate
A local-first MCP server and CLI that forces AI agents to pause risky actions for human approval with durable state and audit logs.
<img src="demo.gif" alt="Demo" width="700" />
</div>
🎯 Why?
Trending repos show agents getting more autonomous, but guardrails are mostly blockers or prompt-level policies. Destructive Command Guard blocks commands, while agent frameworks and channel SDKs still lack a tiny durable human-in-the-loop approval queue that any MCP client or CLI agent can use. approval-gate fills that gap with a single-file SQLite-backed approval gateway, risk scoring, and audit trail.
Target audience: Developers running coding agents, DevOps agents, or MCP-powered assistants who want safe autonomy with explicit human sign-off for risky commands.
✨ Features
- ✨ MCP stdio server with request_approval, list_approvals, resolve_approval, and audit_tail tools
- ✨ CLI for creating, listing, approving, denying, and auditing approval requests
- ✨ Rule-based risk scoring for shell commands with optional auto-approval for low-risk actions
🚀 Quick Start
# Install
pip install approval-gate
# Run
approval-gate --help
📦 Installation
From Source
git clone https://github.com/YOUR_USERNAME/approval-gate.git
cd approval-gate
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
# Install in development mode
pip install -e ".[dev]"
# Run tests
pytest -v
🎬 Demo
The GIF above was recorded using Charm VHS:
vhs < demo.tape
📖 Usage
# Show help
approval-gate --help
# Common usage examples
approval-gate --example
🏗️ Architecture
graph LR
A[Input] --> B[Core Engine]
B --> C[Output]
B --> D[Plugins]
D --> E[Extensions]
🤝 Contributing
Contributions are welcome! Please:
- Fork the repo
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
MIT © 2026 — See LICENSE for details.
<div align="center">
If this project helped you, please ⭐ star it!
</div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.