
AgentGate
io.github.agentkitaiPublished by GitHub account agentkitaiv0.0.3Updated Oct 25, 2026
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
Overview
AgentGate is a human-in-the-loop approval gateway that lets an AI agent submit actions for policy checks and human approval before executing them.
- What you can do
- Submit, read and list approval requests, including status by ID and filtering by status or other criteria, and approve or deny pending requests with a reason. Create, replace and delete approval policies and list them by priority. Read audit log entries with filters and pagination, and list the distinct actors recorded in the audit trail. Requests can be routed to a dashboard, Slack, Discord or email, and webhooks notify external systems of request events.
- When to use it
- Use it when an agent can take consequential actions such as sending email, deleting files or deploying, and you want policies to auto-approve safe actions, auto-deny dangerous ones and send the rest to a human. It suits teams that need an audit trail of agent decisions.
- Requirements
- Runs locally via npx as an MCP server, but needs a reachable AgentGate server (self-hosted with Docker or from source, with SQLite or PostgreSQL). The MCP client configuration supplies AGENTGATE_URL and AGENTGATE_API_KEY; the API key is created at bootstrap and shown once. Optional Slack, Discord and SMTP credentials enable other approval channels.
Installation
In SourceWeft
- Open AgentGate in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
AgentGate
Human-in-the-loop approval system for AI agents.
Agents request. Policies decide. Humans approve.
Keep humans in control of what AI agents can do.
[npm version] [MIT License] [CI] [TypeScript]
Your AI agent wants to send an email, delete a file, or deploy to production. Should it? AgentGate lets you define policies that auto-approve safe actions, auto-deny dangerous ones, and route everything else to a human — via dashboard, Slack, Discord, or email.
✨ Highlights
- 🛡️ Policy engine — auto-approve, auto-deny, or route to humans based on rules
- 👥 Multi-channel approvals — Slack, Discord, email, or web dashboard
- 🔌 TypeScript SDK + MCP — works with any agent framework or Claude Desktop
- 🪝 Webhooks with retry — real-time notifications with exponential backoff
- 📝 Full audit trail — every request, decision, and action logged, each policy decision tagged with the OWASP LLM Top-10 risk it mitigates (compliance evidence)
- 🐳 Docker-ready — one
docker-compose upfor the full stack - 🔐 Production-hardened — SSRF protection, ReDoS defense, structured logging, graceful shutdown
- 🔗 One-click decision links — approve or deny directly from notification emails and webhooks
- ♿ Accessible UI — keyboard-navigable approval modals, focus trapping, ARIA labels
- 💀 Skeleton loading — smooth loading states across every dashboard page
- ⚡ Fast & lightweight — Hono server, SQLite or PostgreSQL
Quickstart
Drop AgentGate into an MCP client (Claude Desktop / Cursor / VS Code) — point it at the gateway:
Dashboard
See all pending requests at a glance, color-coded by urgency so you know what needs attention first.
Approval Requests
Review, approve, or deny requests — filter by status to focus on what matters.
Audit Log
Search through every decision with filters for event type, action, actor, and date range.
Request Detail
Drill into any request to see parameters, context, timeline, and audit trail — with one-click Approve/Deny buttons.
API Keys
Manage API keys with fine-grained scopes, rate limits, and usage tracking. Create, edit, or revoke keys from the dashboard.
Webhooks
Configure webhook endpoints for real-time notifications. Add URLs, pick events, and let AgentGate handle retries automatically.
Login
Sign in with your API key — create one via the CLI or ask your admin.
Table of Contents
- Quick Start
- Architecture
- Packages
- SDK Usage
- CLI
- MCP Integration
- Authentication
- API Endpoints
- Rate Limiting
- Webhooks
- Configuration
- Docker Deployment
- Development
- Troubleshooting
- Contributing
- License
Quick Start
1. Install dependencies
2. Run database migrations
3. Bootstrap (create admin API key)
Save the API key - it's shown once only! Set it in your environment:
4. Start the development environment
5. Run the demo
In a new terminal (with API key set):
6. Open the dashboard
Visit http://localhost:5173 to view and manage approval requests.
Architecture
Packages
SDK Usage
CLI
AgentGate includes a command-line interface for managing approval requests.
Installation
Configuration
Configure the CLI with your server URL and API key:
Configuration is stored in ~/.agentgate/config.json. You can also use environment variables:
Commands
Examples
MCP Integration
AgentGate includes a Model Context Protocol (MCP) server for integration with Claude Desktop and other MCP-compatible clients.
Claude Desktop Configuration
Add to your claude_desktop_config.json:
Available MCP Tools
Authentication
AgentGate uses API keys for authentication. All API requests (except /health) require a valid API key.
API Key Scopes
Using API Keys
HTTP Header:
SDK:
Creating Additional API Keys
API Endpoints
Rate Limiting
AgentGate supports per-API-key rate limiting to prevent abuse and ensure fair usage.
How It Works
- Rate limits use a sliding window algorithm (requests per minute)
- Limits are configured per API key
- When exceeded, requests return
429 Too Many Requests - Rate limit headers are included in all authenticated responses
Rate Limit Headers
Configuring Rate Limits
Set rate limits when creating or updating API keys:
Dashboard
Rate limits can also be managed from the web dashboard under Settings → API Keys.
Webhooks
AgentGate can notify external systems when request events occur.
Setting Up Webhooks
Webhook Events
Webhook Payload
Webhook Signatures
If you provide a secret, requests are signed with HMAC-SHA256:
Verify by computing HMAC-SHA256(secret, body) and comparing.
Webhook Retry
Failed webhook deliveries are retried automatically with exponential backoff. The server scans for pending deliveries and retries them with increasing delays (2^attempts * 1000ms) until successful or the maximum retry count is reached.
Configuration
Environment Variables
File-Based Secrets (_FILE suffix)
For Docker secrets or Kubernetes secret mounts, AgentGate supports a _FILE suffix convention. Instead of setting a secret directly in an environment variable, point to a file containing the value:
Behavior:
- File contents are trimmed of leading/trailing whitespace
- If both the env var and the
_FILEvariant are set, the explicit env var takes precedence - Missing or unreadable files produce a warning but do not crash the server
Example with Docker Compose:
Policy Configuration
Policies are stored in the database and can be managed via API:
Docker Deployment
AgentGate provides Docker images for easy self-hosted deployments.
Quick Start
- Copy the example environment file:
- Generate secure credentials:
- Start all services:
- Access the services:
- Dashboard: http://localhost:3003
- API Server: http://localhost:3002
- Health Check: http://localhost:3002/health
Host ports are configurable via
SERVER_PORT(default3002) andDASHBOARD_PORT(default3003); both map to the container's internal port 3000/80.
Services
* PostgreSQL and Redis are on an internal Docker network (
agentgate-internal) and are not exposed to the host by default. During development,docker-compose.override.ymlis auto-loaded and exposes them on ports 5432/6379. For production, rundocker-compose -f docker-compose.yml up -dto skip the override.
With Slack or Discord Bots
To include the bot services, use the bots profile:
Configuration
All configuration is done via environment variables. See .env.example for all options.
Required variables:
ADMIN_API_KEY— Admin API key (min 16 characters)
Recommended for production:
JWT_SECRET— JWT signing secret (min 32 characters)CORS_ALLOWED_ORIGINS— Restrict to your domain(s)POSTGRES_PASSWORD— Use a strong password
Building Images
Build all images locally:
Build a specific service:
Database Migrations
Migrations run automatically when the server starts. For manual control:
Viewing Logs
Stopping Services
Production Considerations
- Use a reverse proxy (nginx, Caddy, Traefik) for TLS termination
- Set strong passwords for PostgreSQL
- Restrict CORS origins to your domain
- Use Docker secrets for sensitive values in production
- Set up backups for PostgreSQL data volume
- Monitor health endpoints for uptime checks
Development
Testing
AgentGate uses Vitest for testing across all packages.
Coverage reports are generated per-package and include line, branch, and function coverage.
Code Quality
Project Structure
Contributing
Contributions are welcome! To get started:
- Fork the repository
- Clone and install dependencies (
pnpm install) - Follow the Development section above to set up your local environment
- Create a feature branch and make your changes
- Run
pnpm build && pnpm testto verify everything works - Open a pull request
Please make sure all tests pass and code is formatted (pnpm format:check && pnpm lint) before submitting.
🧰 AgentKit Ecosystem
License
MIT
Source: README.md at commit abb46ee
Tools
0Version history
1- v0.0.3LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts