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

Q: How do I stream block updates from Logseq (Knowledge Management) using the Vercel AI SDK?

You call mcpClient.tools() and pass them to streamText. When the model decides to edit a node with updateblock, the SDK streams the tool call and the resulting block structure directly to your React components in real time.

Q: Can I use Logseq (Knowledge Management) to create pages with Vercel AI SDK?

Yes, you can trigger createpage directly from your streaming chat routes. This lets the model generate fresh markdown files on your local drive while showing the user progress block by block.

Q: What happens if a user tries to delete a page?

The model executes deletepage to wipe the markdown file and clear its metadata. Because Vercel AI SDK handles tool execution on your backend, you can add server-side checks before letting the model permanently destroy graph files.

Build live-updating web interfaces that stream blocks and pages directly from your local Logseq graph using Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Logseq (Knowledge Management) to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream local notes to web apps with Vercel AI SDK

Stop making users wait for heavy graph parsing. By pairing this MCP Server with Vercel's streaming capabilities, your application renders outline blocks the second they are pulled from the local file system. It uses `get_page_blocks` to fetch the nested hierarchy and sends it chunk by chunk to your React or Next.js frontend. You do not need complex state management to show updates. When an agent creates a new note using `create_page`, the raw markdown streams straight into the viewport, bypassing typical loading spinners.

Real-time outliner modifications

Outliners rely on strict parent-child relationships that are easy to break. This integration lets your application invoke `insert_block` and `update_block` to modify specific nodes without forcing a full page reload. Because the SDK works directly with edge runtimes, these tools execute fast using our secure MCP setup. Your interface stays perfectly synced with the local graph index while maintaining UUID integrity across every block edit.

Instant local search across graph indices

Digging through thousands of markdown files is slow unless you index them. This setup exposes `search_content` directly to your model, allowing it to crawl local directories and return relevant text blocks instantly. Users get immediate answers from their personal knowledge base. The model calls `get_current_graph` to verify the active workspace before running queries, ensuring it never searches the wrong directory.

Setup guide

Set up Logseq (Knowledge Management) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Logseq (Knowledge Management) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Logseq (Knowledge Management) transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You call `mcpClient.tools()` and pass them to `streamText`. When the model decides to edit a node with `update_block`, the SDK streams the tool call and the resulting block structure directly to your React components in real time.

Yes, the MCP client communicates over HTTP or SSE, which works perfectly in Edge environments. You can run light-weight agents that call `list_pages` and inspect metadata using `get_page` without cold-start delays.

Yes, you can trigger `create_page` directly from your streaming chat routes. This lets the model generate fresh markdown files on your local drive while showing the user progress block by block.

The model executes `delete_page` to wipe the markdown file and clear its metadata. Because Vercel AI SDK handles tool execution on your backend, you can add server-side checks before letting the model permanently destroy graph files.

No, your local Markdown files and block properties remain sandboxed on your machine. This MCP Server runs inside a secure local environment, only exposing specific tool outputs like `search_content` to the LLM when you explicitly run a query.

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