An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Wallabag Pocket (Alternative) to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn your saved articles into an interactive knowledge base.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 11 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 11 available through Wallabag.

  1. 01

    Add tags to entry

    This capability adds specific tags to an entry in your Wallabag library.

  2. 02

    Mark entry read

    Use this to archive an entry by marking it as read.

  3. 03

    Create entry

    This capability saves a new URL directly to your Wallabag instance.

  4. 04

    Delete entry

    Use this to remove an entry from your Wallabag list.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 11 available through Wallabag.

  1. 05

    Get entry

    This capability retrieves the details of a single entry using its ID.

  2. 06

    List annotations

    Use this to pull existing annotations from a specific entry.

  3. 07

    List entries

    This capability fetches all your saved articles from Wallabag.

  4. 08

    List tags

    Use this to see all the tags currently in your Wallabag account.

Capability set03 / 03

09-11

3 capabilities in this set.

Part of 11 available through Wallabag.

  1. 09

    Mark entry favorite

    This capability marks an entry as a favorite or starred item.

  2. 10

    Remove tag from entry

    Use this to strip a specific tag from an entry.

  3. 11

    Create annotation

    This capability lets you write a new annotation or note on an entry.

Real work

What teams actually run

01

Research Summarization

Your agent reads a saved article and summarizes the key points for you.

02

Library Cleanup

You tell your agent to archive all articles tagged as 'read'.

03

Quick Bookmarking

You send a URL from your browser to your agent to save it to Wallabag.

04

Note Taking

You ask your agent to add a specific highlight or note to a saved entry.

Automate a task

Put Wallabag to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Wallabag works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Wallabag to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

963ms average. Fast in production.

Wallabag is checked daily against the live service.

Daily averagePeak 1131ms
Oct 3Today
Fastest day
835ms
Slowest day
1131ms
14-day trend
Improving-6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 11 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Wallabag, so you can see the experience inside your AI.

It does not authenticate your account with Wallabag. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Wallabag Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_9JEcpr65iZOjgRNwUu24ihXNxbnlXHylMUKADJPX/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Wallabag capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "wallabag-pocket-alternative-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_9JEcpr65iZOjgRNwUu24ihXNxbnlXHylMUKADJPX/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Wallabag in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Wallabag owners hand off.

This MCP is built for people who maintain their own reading lists and want to use AI to process their research.

  • 01

    Researchers

    They save sources and use the AI to summarize findings from their annotations.

  • 02

    Knowledge Workers

    They manage large article backlogs and use natural language to find specific info.

  • 03

    Privacy Enthusiasts

    They keep their data on self-hosted servers while using AI for insights.

FAQ

Questions Wallabag owners ask.

  • 01

    What is this MCP used for?

    It connects your self-hosted Wallabag instance to your AI client so you can manage, tag, and read your saved articles through your agent.

  • 02

    Which AI clients can I use?

    You can use this MCP with any compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Do I need to host Wallabag myself?

    Yes, this MCP is designed to connect to your existing Wallabag instance.

  • 04

    Can I add tags to my articles using the AI?

    Yes, you can use the add_tags_to_entry capability to organize your articles via your agent.

  • 05

    Is my data private?

    Since you are connecting to your own self-hosted Wallabag instance, you maintain control over your reading data.

  • 06

    Can I save a new article just by providing a URL?

    Yes! Use the create_entry capability with the URL you want to save. Your agent will add it to your Wallabag account immediately.

  • 07

    How do I archive an article once I've finished reading it?

    Simply ask the agent to mark the article as read using the mark_entry_read capability with the specific Entry ID.

  • 08

    Can I see the highlights and notes I've made on an article?

    Yes. The list_annotations capability retrieves all highlights and notes associated with a specific Entry ID, allowing the AI to reference your personal insights.

Explore

More in Productivity

Suggestions

Connect Wallabag to Claude, Cursor, ChatGPT & more