How to Use the Logseq (Knowledge Management) MCP in Mastra AI

Q: Can I require human approval before deleting pages in Logseq (Knowledge Management) with Mastra AI?

Yes, you can configure requireToolApproval on the agent before it calls deletepage. This pauses the workflow and waits for your confirmation before removing the file from your local disk.

Q: How does the agent discover what pages are available?

The agent calls listpages to get an array of all page names in your active graph. It can then pass those names to getpageblocks to map out the entire outline structure before making edits.

Build resilient knowledge workflows that auto-retry page creation and block updates in Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Logseq (Knowledge Management) MCP to Mastra AI

Create your Vinkius account to connect Logseq (Knowledge Management) to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Logseq (Knowledge Management) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated graph maintenance workflows

Mastra AI lets you build multi-step workflows that handle graph errors without crashing. If a call to `insert_block` fails because a file is locked, the workflow engine automatically retries with exponential backoff until the block is safely written. You can set up conditional branching based on what the graph contains. The agent runs `get_page` to check if a topic exists, then either appends blocks to it or spins up a fresh file using `create_page`.

Safe block deletion with Mastra AI

Deleting nodes in an outliner is risky because you can easily orphan child blocks. By using the framework's step-based logic, you can safely call `delete_block` and guarantee that dependent nodes are cleaned up in a specific order. If any step in your deletion pipeline fails, Mastra rolls back the changes. This protects your local markdown files from half-finished edits and keeps your graph structure clean.

Graph indexing via MCP Server tools

Managing thousands of blocks requires a reliable index check. This MCP Server exposes `get_current_graph` so your agents can verify they are working in the correct local directory before executing heavy operations. Once verified, the agent uses `search_content` to locate specific keywords across your notes. It then parses the results to trigger follow-up workflow steps, like updating metadata tags on older pages.

Setup guide

Set up Logseq (Knowledge Management) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Logseq (Knowledge Management) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "logseq-knowledge-management-mcp-client",
  servers: {
    "logseq-knowledge-management-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Logseq (Knowledge Management) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Logseq (Knowledge Management) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Logseq (Knowledge Management) transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Logseq. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Logseq (Knowledge Management) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Logseq (Knowledge Management) MCP in Mastra AI

You register the MCP tool inside a Mastra workflow step. The framework automatically retries the operation if your local markdown file is temporarily locked by another process.

Yes, you can configure `requireToolApproval` on the agent before it calls `delete_page`. This pauses the workflow and waits for your confirmation before removing the file from your local disk.

You register the MCP tool with your Mastra agent. The agent executes local queries against your graph indices and returns the matching text blocks directly into your workflow state.

The agent calls `list_pages` to get an array of all page names in your active graph. It can then pass those names to `get_page_blocks` to map out the entire outline structure before making edits.

Zero data leaves your machine. The local graph database files and page UUIDs are read locally by the MCP Server on your device, and only the specific text requested by your active workflow step is processed.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript