Overview

Pinako AI Bridge exposes your tab trees, libraries, notes, tags, memos, and chronology to external AI clients through the Model Context Protocol (MCP). Once connected, your AI assistant can search, browse, and answer questions about everything in your Pinako workspace using natural language.

The bridge runs locally on your machine. Your data stays on your computer and is never sent to a third-party server. The AI client's own model handles all reasoning.

How It Works

The bridge consists of two parts that run together:

1. Chrome Native Messaging host: a local process that communicates with the Pinako extension via Chrome's native messaging protocol, receiving your live tab tree data.
2. MCP server: an HTTP server on localhost:37421 that serves your data to AI clients using the standard MCP protocol.

When an AI client asks about your tabs, the MCP server responds from its in-memory cache of your latest tree data. The extension pushes updates automatically whenever your tabs change.

Quick Start

1. Download and run the installer.
   • Windows: Run the graphical installer. It detects your AI apps and displays a checklist. Select some or all of them, and it configures them automatically.
   • Linux: Download the CLI executable for your architecture (x64 or ARM64), make it executable (chmod +x), and run it from a terminal. It walks you through the same detection and configuration steps.

     chmod +x pinako-ai-bridge-cli-linux-x64
     ./pinako-ai-bridge-cli-linux-x64

2. Restart your AI apps. Close and reopen any configured apps so they pick up the new MCP settings.
3. Activate the connection. Click the Pinako icon in your browser toolbar to open the extension. This starts the bridge.
4. Ask your AI. Try something like "What tabs do I have open?" or "Find my tabs about machine learning."

Supported AI Clients

The installer auto-detects and configures the following clients:

Client	Platform	Config type
Claude Code	Win / Linux	JSON (stdio)
Claude Desktop	Win / Linux	JSON (stdio)
Cursor	Win / Linux	JSON (stdio)
Windsurf	Win / Linux	JSON (stdio)
Cline (VS Code)	Win / Linux	JSON (stdio)
Roo Code (VS Code)	Win / Linux	JSON (stdio)
Continue.dev	Win / Linux	JSON (stdio)
Any HTTP MCP client	Any	URL endpoint

For clients that use the stdio transport, the installer writes to the app's MCP config file. For HTTP clients, point them at:

ChatGPT Desktop

ChatGPT Desktop isn't in the auto-configure list above. OpenAI's MCP connector system accepts only public HTTPS URLs and rejects loopback addresses like 127.0.0.1 with an "Unsafe URL" error. Since the bridge runs at http://localhost:37421/mcp on your own machine, ChatGPT Desktop can't reach it directly.

If you already run a tunneling service that gives the bridge a public HTTPS URL (Cloudflare Tunnel, ngrok, Tailscale Funnel, or similar), you can connect ChatGPT manually:

1. Start your tunnel pointing at 127.0.0.1:37421. You will get a public HTTPS URL such as https://your-tunnel.example/mcp.
2. Open ChatGPT Desktop and turn on Developer Mode under Settings → Apps & Connectors → Advanced. This requires a ChatGPT Pro, Team, Enterprise, or Edu plan.
3. Go to Settings → Connectors → Create. Paste your tunnel URL and save.
4. Open the Pinako extension popup so the bridge starts running.
5. Ask ChatGPT a question that uses Pinako (for example, "List my Pinako libraries").

What your AI can see

Your AI client has access to your Pinako workspace through these capabilities:

• See your full tab tree (get_tree). Every window, group, and tab, including titles, URLs, favicons, your memos, your tags, opened-dates, and which tabs are ghost (closed) versus live.
• Search your tabs by keyword or tag (search_tabs). Matches against titles, URLs, memo text, and tags. Prompts like "find my tabs tagged science" or "which tabs mention machine learning" work directly.
• List your saved libraries (list_libraries). Names, descriptions, and tab counts.
• Read inside a specific library (get_library). Folders, tabs, your memos, your tags, and any notes attached to that library.
• Read your main-tree notes (get_global_notes). The top-level notebook documents that aren't attached to any library.
• See which browsers you're running (list_browsers). When Pinako is open in more than one browser, the AI can target a specific one ("my Brave tabs", "list libraries from Chrome").

The AI Bridge exposes only tab-tree and library data. Your bookmarks, subscription, and sync history aren't accessible.

Troubleshooting

AI client can't connect

1. Make sure the Pinako extension is open (click the toolbar icon).
2. Check that the bridge process is running:
   • Windows: Look for pinako-mcp-service.exe in Task Manager.
   • Linux: Run pgrep -f pinako-mcp-service.
3. Verify the MCP config entry exists in your AI client's settings.
4. Restart the AI client after configuration changes.

Bridge stops when extension closes

The bridge runs as a Chrome native messaging host — it starts when the extension opens and stops when it closes. Keep the Pinako popup open while using AI tools.

Port conflict

If port 37421 is already in use, the bridge will fail to start. Check for other processes using that port and stop them.

Uninstalling

Windows

Run Add or Remove Programs and uninstall Pinako AI Bridge. This removes the native host, the MCP server, and the native messaging manifest. You may also want to remove the "pinako" entry from each AI app's MCP config file.

Linux

1. Delete the ~/.local/share/pinako/ folder (contains the MCP service and native host manifest).
2. Remove the "pinako" entry from the MCP config file of each AI app you configured.
3. (Optional) Delete the native messaging host symlinks:
   ~/.config/google-chrome/NativeMessagingHosts/com.pinako.mcp.json
~/.config/chromium/NativeMessagingHosts/com.pinako.mcp.json