Chrome Reading List MCP
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., "@Chrome Reading List MCPWhat's on my reading list about AI agents? Summarize the three newest."
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.
Chrome Reading List MCP
Let your AI assistant read and tidy up your Chrome reading list — the "Add to reading list" items in Chrome's side panel.
Works with any MCP client: Claude Desktop, Claude Code, Cursor, Codex, opencode, Kilo, Windsurf, VS Code and more.
Things you can ask:
"What's on my reading list about AI agents? Summarize the three newest."
"Group my unread items by topic and tell me which ones are older than a month."
"I've read the Rust and Postgres articles — mark them as read."
"Remove everything from news sites I added before June."
"Add these five links to my reading list."
"Export my reading list as Markdown."
Setup (about 2 minutes)
You need Chrome 120 or newer and Node.js 18 or newer.
1. Install the Chrome extension
Download
extension.zipfrom the latest release and unzip it.Open
chrome://extensions, turn on Developer mode (top right).Click Load unpacked and pick the unzipped
extensionfolder.
The extension only has the readingList permission and only talks to your own computer (127.0.0.1).
2. Add the server to your AI client
Claude Code
claude mcp add -s user chrome-reading-list -- npx -y github:ZhenningLang/chrome-reading-list-mcpClaude Desktop — Settings → Developer → Edit Config, then add:
{
"mcpServers": {
"chrome-reading-list": { "command": "npx", "args": ["-y", "github:ZhenningLang/chrome-reading-list-mcp"] }
}
}Cursor — same JSON in ~/.cursor/mcp.json.
Codex — add to ~/.codex/config.toml:
[mcp_servers.chrome-reading-list]
command = "npx"
args = ["-y", "github:ZhenningLang/chrome-reading-list-mcp"]opencode — add to ~/.config/opencode/opencode.json:
{
"mcp": {
"chrome-reading-list": {
"type": "local",
"command": ["npx", "-y", "github:ZhenningLang/chrome-reading-list-mcp"],
"enabled": true
}
}
}Kilo CLI — same block in ~/.config/kilo/kilo.json.
Restart the client. That's it.
3. Check it works
npx -y github:ZhenningLang/chrome-reading-list-mcp doctorOK: connected, 365 entries in the reading list means you're set.
Related MCP server: mcp-bookmark-server
Tools
Tool | What it does |
| List entries; filter by read/unread and keywords; always reports the total count |
| Add pages (skips ones already there) |
| Mark read/unread, rename |
| Remove by URL — backs up the whole list first |
| Bring entries back from a backup |
| Save the list as Markdown, JSON or CSV |
Safety
Nothing leaves your computer. The extension talks only to the server on
127.0.0.1; the server talks only to your AI client.Websites can't use it. The server only accepts the extension's own origin.
Deletes are undoable. Every removal first saves the full list to
~/.chrome-reading-list-mcp/backups/; ask your assistant to restore from it.Your AI assistant does see your reading list titles and URLs when it uses these tools — that's the point, but keep it in mind.
Troubleshooting
"The Chrome extension is not connected" — make sure Chrome is open and the extension is enabled. If the toolbar icon shows
…, it's waiting for the server; the AI client starts the server when it launches.Several AI clients at once is fine: the first one hosts the connection and the others share it.
Port 17893 is taken by something else — not configurable yet; please open an issue.
Development
npm install
npm test # unit tests with a fake extension
npm run test:e2e # real Chrome for Testing + the real extensionLicense
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Save and organize web finds in persistent, user-controlled collections for AI assistants.
- LeafOAuthapp.readwithleaf
AI assistant integration for Leaf — track books, log reading sessions, and manage your library.
The media memory layer for AI agents and their humans. Your AI client gets 29 tools to search your collection, add items, update ratings, preview music, and find patterns across everything you've read, watched, and listened to.
Academic literature search, retrieval, and private library management on top of OpenAlex.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to search and analyze Chrome browser history and bookmarks data locally, including keyword searches, date range filtering, recent browsing activity, and usage statistics across all platforms.2-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to save and search bookmarks using OpenAI's RAG capabilities for intelligent bookmark management and retrieval.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to control Chrome browser operations such as navigation, reading pages, taking screenshots, managing tabs, and more via a Chrome extension and native messaging.MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude to search, reorganize, and clean up Chrome bookmarks with an interactive review UI and real undo support across Chromium-based browsers.18 npmMIT