How to Use the Capacities MCP in Vercel AI SDK

Q: How do I search Capacities with the Vercel AI SDK?

Use the lookup tool. You pass it a search query, and it returns matching objects from the user's space. With the AI SDK, those results will stream directly into your UI components.

Q: Can I create new pages or objects in Capacities using the Vercel AI SDK?

Yes, that's what the createobject tool is for. You define the object's type and its properties in your code, and the tool adds the new item to the user's Capacities space.

Q: What kind of data structures can my Vercel AI SDK app get from Capacities?

You can get the entire schema of a space. The getstructures tool returns all object type definitions, so your app knows exactly what fields and properties are available for any custom object a user has.

Q: How do I list all available spaces for a user?

The listspaces tool returns an array of all spaces in the connected account. This is useful for building a dropdown so the user can choose where to save or search for content.

Stream Capacities data directly into your React components with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Capacities MCP to Vercel AI SDK

Create your Vinkius account to connect Capacities 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 Capacities with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live knowledge graph UIs

This MCP Server gives your app read-access to a user's Capacities. Use the `lookup` and `get_object` tools to fetch notes and structured data. Because you're using the Vercel AI SDK, that data streams directly into your UI components as it arrives. Your app can also understand the structure of the data before it even gets there. Call `get_space_info` and `get_structures` to see every object type and property a user has defined. You can use this to dynamically generate forms and displays that perfectly match their setup.

Capture notes and links instantly

Your UI can write data straight to Capacities. Let users drop a URL into a text field, and your code calls `save_weblink` to create a new, properly formatted web link object in their space. It works for quick thoughts, too. The `save_to_daily_note` tool appends any text you send to the user's daily note. Your job is just to build the frontend; this server handles the connection and the action.

Organize content with the Vercel AI SDK

Let your users create new, structured objects in their knowledge base from your app. The `create_object` tool takes a type and a set of properties, then generates a new item in their Capacities space. It's perfect for building custom input forms. You can also manage organization on the fly. The `add_tag` tool applies a tag to an existing object. This lets your users connect ideas and group related content without ever leaving your application.

Setup guide

Set up Capacities 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 Capacities 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 Capacities 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 Capacities. 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 Capacities 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 Capacities MCP in Vercel AI SDK

Use the `lookup` tool. You pass it a search query, and it returns matching objects from the user's space. With the AI SDK, those results will stream directly into your UI components.

Yes, that's what the `create_object` tool is for. You define the object's type and its properties in your code, and the tool adds the new item to the user's Capacities space.

You can get the entire schema of a space. The `get_structures` tool returns all object type definitions, so your app knows exactly what fields and properties are available for any custom object a user has.

The `list_spaces` tool returns an array of all spaces in the connected account. This is useful for building a dropdown so the user can choose where to save or search for content.

This server only touches Capacities object data, notes, and tags when your code explicitly calls a tool. Connections are ephemeral and run in a Vinkius sandbox. Your app authenticates with a single token, so it never handles or stores user credentials.

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