This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
A local browser-automation bridge that lets AI agents drive your real browser — your actual login sessions, cookies, and tabs — instead of a cloud sandbox or headless instance. Konnect connects MCP-compatible coding agents (and a token-cheap CLI) to Comet Browser via a long-lived daemon and a Chrome MV3 extension.
Status: production. Runs on macOS via launchd (port 9223).
A persistent aiohttp daemon (daemon/, listens on :9223) owns the WebSocket to
a Chrome MV3 extension (extension/) that performs the actual page interaction;
the WS survives MV3 service-worker eviction via an offscreen document. Two thin
clients front the daemon's HTTP API: an MCP stdio shim (mcp/) for AI agents and
a CLI (cli/) for low-token coding. The daemon is the single source of truth —
MCP is one client, not the only interface.
See ARCHITECTURE.md for full design rationale and the
decision tree (why daemon-over-MCP, why snapshot-first, why CLI+SKILL alongside MCP).
Related MCP server: agent-browser-mcp
konnect/
├── daemon/ # aiohttp daemon: /command /ws /health (the persistent core)
├── extension/ # Chrome MV3 extension (service worker + content script + offscreen WS)
├── mcp/ # MCP stdio server — thin shim → daemon HTTP
├── cli/ # argparse CLI → daemon HTTP (token-cheap)
├── skill/ # SKILL.md — agent operating instructions
├── tests/ # isolated test harness (disposable Chromium + CDP)
├── deploy/ # launchd plist template + install.sh
└── docs/ # operations notes# 1. Python deps (aiohttp for the daemon)
pip install -e .
# 2. Install + start the daemon under launchd
deploy/install.sh
# 3. Load the extension (one-time, manual)
# chrome://extensions (or comet://extensions) → Developer mode → Load unpacked
# → choose this repo's extension/ directorydeploy/install.sh auto-detects a Python with aiohttp (or takes an explicit
path: deploy/install.sh /path/to/python). It renders local.konnect.daemon.plist
with your $HOME and repo path — no hardcoded user paths.
Verify the daemon sees the extension:
curl http://127.0.0.1:9223/health # → {"extension_connected": true}Logs: /tmp/konnect-daemon.log. Stop: launchctl unload ~/Library/LaunchAgents/local.konnect.daemon.plist.
Wire mcp/konnect_mcp.py as an MCP server in your agent (Claude, Cursor, opencode).
Exposed tools (all proxy to the daemon over HTTP):
Tool | Purpose |
| Check daemon + extension connection |
| List open browser tabs (group + blocked state) |
| Select an already-open tab by URL prefix |
| Open a URL (new background tab by default) |
| AX-style accessibility tree with |
| Click an element by ref |
| Fill an input/textarea/select/contenteditable by ref |
| Capture tab/element to a PNG file (read via |
| Visible text of the current tab |
| Run JS in the page main world (fallback for ref limits) |
Targeting is snapshot-first: call konnect_snapshot, read the ref=N tags, then
konnect_click/konnect_fill by ref. Screenshots write to disk and are read with
Read — never base64 into context.
Bearer-token auth (extension/token.json), generated by the daemon; tokens are
git-ignored and never committed.
evaluate runs in the MAIN world for trusted local use only. Sites that check
event.isTrusted may reject synthetic events — a product boundary, not a bug.
MIT. Clean-room implementation; see ARCHITECTURE.md.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Let AI agents use your real, signed-in Chrome: tabs, clicks, forms, screenshots and video.
Let your AI agent operate any website through a real, logged-in browser session.
Let AI agents use any website you're logged in to. Sessions stay encrypted on your machine.
Connect AI agents to your own Chrome with scoped access, approvals, and verified task results.
