Enables interaction with Discord via real browser control, allowing actions like sending messages, navigating servers, and more without separate API keys.
Enables interaction with Gmail via real browser control, allowing actions like reading inbox, sending emails, and more without separate API keys.
Enables interaction with Messenger via real browser control, allowing actions like sending messages, replying to conversations, and more without separate API keys.
Enables interaction with Slack via real browser control, allowing actions like sending messages, navigating channels, and more without separate API keys.
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., "@npc message Tim on Slack that deploy is done"
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.
npm i -g npc-agentYour IDE agent says what to do ("message Anna on Slack"). NPC does it in your real, logged-in browser. No API keys per service, no OAuth, no bot accounts. Works with any MCP IDE - Cursor, VS Code, Windsurf.
You want to | Your IDE says |
Message someone on Slack | "go to slack and message #general: deploy is done" |
Reply on Messenger | "open messenger and reply to Anna: sounds good" |
Check Gmail | "take a screenshot of my gmail inbox" |
Fill out a form | "find the email field, click it, type my address, press Tab" |
Do it all in one shot | use |
Related MCP server: agentify-desktop
Install: npm i -g npc-agent
Load the extension: chrome://extensions > Developer mode > Load unpacked > select npc-cli/extension/
Add to .cursor/mcp.json or .vscode/mcp.json:
{
"mcpServers": {
"npc": {
"command": "node",
"args": ["/path/to/npc/npc-cli/dist/index.js"]
}
}
}Click the NPC icon on any tab. Green badge means connected.
IDE (Cursor / VS Code) NPC Server Browser
| | |
|--- MCP stdio ------------->| |
| "click Send button" |--- WebSocket :7221 -->|
| | |--- CDP (chrome.debugger)
| | |--- clicks in real tab
| |<-- result ------------|
|<-- tool response ----------| |The IDE handles reasoning. NPC just executes browser actions via Chrome DevTools Protocol. No LLM inside NPC.
Tool | What it does |
| Capture tab as PNG |
| Go to a URL |
| Click at (x, y) |
| Type text into focused element |
| Press Enter, Tab, Escape, arrows |
| Scroll up/down/left/right |
| Find element by CSS selector or text, returns (x, y) center |
| Run multiple actions in one call |
| Run JavaScript in page context |
| Get all text from the page |
| Get full page HTML |
| Get current tab URL |
| Get current tab title |
| Fetch any URL with browser cookies (bypasses CORS) |
| Check Microsoft Teams for unread messages |
One MCP call instead of four:
[
{"action": "find", "selector": "Message Anna"},
{"action": "click", "x": 450, "y": 320},
{"action": "type", "text": "hey, deploy is done"},
{"action": "key", "key": "Enter"}
]Chrome and Brave only (uses chrome.debugger API). One active tab at a time per extension instance. Cannot attach to chrome://, brave://, or extension pages. Screenshot coordinates are at device pixel ratio - divide by DPR before clicking on HiDPI displays.
Requires Node.js >= 18.
This server cannot be deployed
Live browser debugging for AI assistants — DOM, console, network via MCP.
Hyperbrowser MCP — wraps the Hyperbrowser AI-agent browsing API
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
