An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Logseq Knowledge Management 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. Talk to your local graph to organize and retrieve your notes.

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 · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Logseq.

  1. 01

    Insert block

    This capability adds new outliner chunks to your Logseq map. It handles properties and updates nodes immediately.

  2. 02

    Get current graph

    This capability identifies your active graph environment. It parses the current graph arrays to verify your connection.

  3. 03

    Update block

    This capability modifies existing outliner blocks. It preserves your UUID bounds and linking indices during the update.

  4. 04

    Delete block

    This capability removes specific blocks from your graph. It safely drops child dependencies when a node is deleted.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Logseq.

  1. 05

    Get page blocks

    This capability pulls the hierarchical block tree from a specific page. It returns the native array of blocks for that page.

  2. 06

    Search content

    This capability runs local queries across your graph. It finds text targets within your indices and titles.

  3. 07

    Create page

    This capability deploys new pages into your local graph. It includes native markdown content for the new page.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Logseq.

  1. 08

    Delete page

    This capability removes an entire page from your graph. It wipes the content arrays and associated metadata loops.

  2. 09

    Get page

    This capability retrieves metadata for a specific page. You can find it using a page name or a UUID.

  3. 10

    List pages

    This capability provides a full list of all pages currently in your Logseq graph.

Real work

What teams actually run

01

Automated Note Taking

Tell your agent to create a new journal entry and add specific bullet points from a meeting.

02

Research Synthesis

Ask your agent to find all mentions of a specific topic across different pages and namespaces.

03

Graph Maintenance

Use the agent to clean up old pages or reorganize block hierarchies.

04

Technical Documentation

Update project logs and technical notes directly from your development environment.

Automate a task

Put Logseq 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

Logseq 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 Logseq 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

946ms average. Fast in production.

Logseq is checked daily against the live service.

Daily averagePeak 1259ms
Oct 3Today
Fastest day
766ms
Slowest day
1259ms
14-day trend
Slowing+7%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 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 Logseq, so you can see the experience inside your AI.

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

Logseq Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_kMDKB03kxqJ9X26G0WlmNUknXtj6UN59p0KJSs7t/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 — Logseq capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "logseq-knowledge-management-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_kMDKB03kxqJ9X26G0WlmNUknXtj6UN59p0KJSs7t/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 Logseq in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Logseq owners hand off.

This is built for people who use Logseq as their primary thinking capability and want to interact with their notes using an AI agent.

  • 01

    Knowledge Workers

    They hand off the task of organizing research and meeting notes to their agent.

  • 02

    Software Developers

    They manage technical docs and project logs directly from their IDE or terminal.

  • 03

    PKM Enthusiasts

    They use the agent to audit graph structures and perform bulk updates to keep their graph clean.

FAQ

Questions Logseq owners ask.

  • 01

    How do I connect my local Logseq to this MCP?

    You need to enable the HTTP API in your Logseq settings and then provide your API Token and Host URL (like http://localhost:12315) to the connector.

  • 02

    Does this MCP store my notes?

    No. This MCP connects to your local Logseq instance. Your data stays in your local graph, maintaining your privacy-first workflow.

  • 03

    Can I use this with Cursor or VS Code?

    Yes. This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 04

    Will editing blocks break my existing links?

    No. The update capability is designed to preserve UUID bounds and linking indices within your graph.

  • 05

    Can I delete pages through my AI agent?

    Yes. You can use the delete page capability to remove content and metadata loops from your graph.

  • 06

    Can I search across all my Logseq pages using my agent?

    Yes. Use the search_content capability to execute deep property searches across your graph indices. Your agent will filter titles, namespaces, and block scopes to find the exact information you need.

  • 07

    How do I add a new note to a specific page?

    Use the insert_block capability and provide the target Page name or ID. Your agent will drive the Logseq editor to add a new outliner chunk with your markdown content immediately.

  • 08

    Can my agent retrieve the hierarchical structure of a long page?

    Absolutely. The get_page_blocks capability extracts the full hierarchical tree from a page map. Your agent will return the nested arrays of outliner blocks, ensuring you have the complete structural context of your data.

Explore

More in Loved By Devs

Suggestions

Connect Logseq to Claude, Cursor, ChatGPT & more