How to Use the Knackly MCP in Vercel AI SDK

Q: How do I connect Vercel AI SDK to Knackly?

Install ai and @ai-sdk/mcp. Configure createMCPClient with your HTTP transport URL and pass mcpClient.tools() directly into streamText.

Q: Can the Vercel AI SDK agent read existing Knackly records?

Yes. It uses listdatarecords to query previous entries and getrecorddetails to pull the specific field data back into your application state.

Q: Do I need to close the MCP connection in my Next.js app?

You do. Always call mcpClient.close() when your route handler finishes to prevent memory leaks in your Vercel edge environments.

Stream legal document generation straight into your Next.js frontend using the 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 Knackly MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map templates via Vercel AI SDK

Your frontend needs to know what templates exist before users can fill them out. The `list_workspaces` and `list_catalogs` tools let your application fetch available document categories on the fly. Once a user selects a category, the agent calls `list_data_models` to pull the exact field requirements. You stream these requirements directly into your React components so users only see the inputs they actually need.

Push records from the UI

When users hit submit on your frontend form, the agent takes that payload and executes `create_data_record`. This pushes the raw data into the engine to process the conditional logic. You don't leave users waiting in the dark. Call `get_record_details` to verify the inputs landed correctly, and stream the confirmation back to the UI instantly.

Fetch finished files with this MCP Server

Generating complex legal documents takes computation. Once the engine finishes assembling the text, your agent uses `list_generated_documents` to grab the final outputs. If your app relies on background updates, `list_webhooks` lets the agent verify which endpoints are configured to ping your Vercel Edge Functions when a document is ready for download.

Setup guide

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

Install `ai` and `@ai-sdk/mcp`. Configure `createMCPClient` with your HTTP transport URL and pass `mcpClient.tools()` directly into `streamText`.

Yes. It uses `list_data_records` to query previous entries and `get_record_details` to pull the specific field data back into your application state.

You do. Always call `mcpClient.close()` when your route handler finishes to prevent memory leaks in your Vercel edge environments.

The agent doesn't process the logic. The platform handles the conditional branching internally. Your agent just supplies the flat data.

Vinkius runs this MCP server in an ephemeral V8 Isolate Sandbox. When your frontend streams sensitive contract clauses or personal identifiers to the API, the sandbox destroys all memory immediately after the request completes. Zero persistence.

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