How to Use the Craft (Docs & Notes) MCP in Vercel AI SDK

Q: How do I handle document search in Craft (Docs & Notes) using Vercel AI SDK?

Call searchdocuments within your agent's tool declaration block. The MCP Server streams the text matches directly to your UI, letting users see search results in real time. Remember to run mcpClient.close() once the streaming session terminates to prevent memory leaks.

Q: Can I append content to a Craft (Docs & Notes) page inside a Vercel AI SDK edge function?

Yes, the appendblock tool executes perfectly within Vercel's Edge Runtime. You just initialize the client using createMCPClient with your Vinkius HTTP endpoint and pass the tools to streamText.

Q: What is the best way to clean up connections between Craft (Docs & Notes) and Vercel AI SDK?

Always invoke mcpClient.close() in your backend cleanup routine or at the end of the edge execution. This releases the SSE transport resources held by the MCP gateway. Failing to do this can exhaust your active connection limits quickly.

Feed live Craft documents directly into your Vercel AI SDK streams without blocking your UI thread.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Craft (Docs & Notes) MCP to Vercel AI SDK

Create your Vinkius account to connect Craft (Docs & Notes) 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 Craft (Docs & Notes) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live document sourcing for Next.js views

Querying your Craft workspace happens instantly when your Next.js app calls `list_documents` through this Vercel AI SDK setup. Instead of making your users stare at a blank loading screen, the server pushes the active folder structure right into the edge stream. Your interface stays responsive because the raw JSON payload from `get_document` feeds straight into the frontend component. You don't have to write custom API endpoints to bridge the gap between Craft.do and your UI.

Real-time block injection on the Edge

Modifying notes on the fly requires the `append_block` tool to write structural properties directly into your live Craft pages. The Vercel AI SDK handles these mutations inside edge functions, keeping execution latency under a hundred milliseconds. When your user requests a new section, the agent invokes `update_document` to swap out outdated text blocks instantly. The resulting layout changes render on the client side without triggering a full page reload.

Syncing Craft tasks via Vercel AI SDK

Tracking action items across folders relies on `list_tasks` to extract checklists directly from your active Craft workspace. This MCP Server translates those rich-text nodes into clean JSON arrays that your agent parses on the fly. By feeding these tasks into your Vercel AI SDK stream, you let users check off items and immediately trigger `update_document` to write the status back to Craft. This eliminates the lag between user action and database state.

Setup guide

Set up Craft (Docs & Notes) 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 Craft (Docs & Notes) 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 Craft (Docs & Notes) 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 Craft. 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 Craft (Docs & Notes) 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 Craft (Docs & Notes) MCP in Vercel AI SDK

Call `search_documents` within your agent's tool declaration block. The MCP Server streams the text matches directly to your UI, letting users see search results in real time. Remember to run `mcpClient.close()` once the streaming session terminates to prevent memory leaks.

Yes, the `append_block` tool executes perfectly within Vercel's Edge Runtime. You just initialize the client using `createMCPClient` with your Vinkius HTTP endpoint and pass the tools to `streamText`.

Always invoke `mcpClient.close()` in your backend cleanup routine or at the end of the edge execution. This releases the SSE transport resources held by the MCP gateway. Failing to do this can exhaust your active connection limits quickly.

Vinkius manages the underlying OAuth handshake with Craft.do on your behalf. This MCP setup handles token rotation automatically, so you only need to configure the authProvider parameter once in your project dashboard.

Absolutely. Your private Craft documents, blocks, and tasks are processed inside isolated V8 sandboxes that vaporize the moment your API request completes. No workspace content is cached or stored on Vinkius servers after the stream ends.

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