AgentGate

MCP server that gives AI agents a browser with your Google session. The agent sees screenshots, decides what to click, and grabs API keys from any service.

How it works

You: "Get me a Twelve Labs API key"

Agent: get_or_create_key("twelvelabs")        → no key cached
Agent: open_browser("https://twelvelabs.io")   → sees screenshot
Agent: click("Sign in with Google")            → sees dashboard
Agent: goto("https://twelvelabs.io/api-keys")  → sees API keys page
Agent: click("Create API Key")                 → sees new key
Agent: extract_text(".api-key")                → reads the key
Agent: save_key("twelvelabs", "tl_key_abc...")  → cached for next time
Agent: close_browser()                         → done

The AI agent is the brain. AgentGate is the hands.

Install

npm install -g agentgate-mcp

Requires Node.js 23+.

Setup (one time)

agentgate login

Opens Chromium — sign into Google, close the browser. Done.

Add to Claude Code

agentgate setup

One command — registers the MCP server and auto-approves all tools so Claude never pauses for confirmation.

claude mcp add agentgate -- agentgate serve
claude config add allowedTools "mcp__agentgate__*"

MCP Tools

| Tool | What it does | |------|-------------| | get_or_create_key | Check if a key is cached for a service | | open_browser | Open browser with Google session, go to URL, return screenshot | | browser_action | Click, fill, scroll, extract text — returns screenshot after each action | | save_key | Store an API key the agent found | | close_browser | Close the browser | | list_my_keys | List all stored keys | | revoke_key | Delete a stored key |

open_browser

{ "url": "https://platform.openai.com/signup" }

Returns a screenshot of the page so the agent can see it.

browser_action

{ "action": "click", "selector": "text=Sign in with Google" }
{ "action": "fill", "selector": "input[name=email]", "value": "[email protected]" }
{ "action": "goto", "url": "https://platform.openai.com/api-keys" }
{ "action": "extract_text", "selector": ".api-key" }
{ "action": "scroll", "value": "500" }
{ "action": "press", "key": "Enter" }
{ "action": "wait", "selector": ".loaded", "ms": 5000 }
{ "action": "screenshot" }
{ "action": "extract_all_text" }

Every action returns a screenshot so the agent always sees what happened.

save_key

{ "service": "openai", "api_key": "sk-..." }

get_or_create_key

{ "service": "openai" }

Returns cached key or { "exists": false }.

Commands

| Command | Description | |---------|-------------| | agentgate login | Sign in with Google (opens browser) | | agentgate serve | Start MCP server | | agentgate doctor | Health check |

Security

• Google session stays on your machine (~/.agentgate/browser-profile/)
• API keys stored in local SQLite database
• No cloud, no telemetry
• The agent can only use YOUR authenticated session

Development

git clone https://github.com/junaid-mahmood/Agent-Gate.git
cd Agent-Gate
npm install
npx playwright install chromium
npm test

License

MIT