How to Use the Jasper MCP in Vercel AI SDK

Q: Can I retrieve brand voices from Jasper inside Vercel AI SDK Edge Functions?

Yes. You can call listvoices and getvoice within your Edge runtime to fetch brand profiles. This lets you apply those profiles to your generation calls without adding latency.

Q: Do I need to manually parse the input schemas for templates?

No. You call gettemplate to fetch the input schema, then pass those exact fields as JSON parameters to runtemplate.

Q: How does this MCP Server secure my company style guides and brand voices?

All style guides and voice profiles retrieved via liststyles and getvoice run in an isolated V8 sandbox on Vinkius. Your brand assets are never cached, stored, or used for model training.

Render Jasper content templates directly into your React components with 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 Jasper MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Jasper templates inside Vercel AI SDK stream

Stop making users wait for marketing copy to load. It's a terrible experience. This MCP Server lets your React application call `run_template` and stream the Jasper output directly to your Vercel AI SDK frontend. Before triggering the generation, your code can pull the exact schema using `list_templates` or `get_template`. This ensures the input JSON matches what the Jasper API expects before the Vercel AI SDK stream even begins.

Maintain strict brand voice on the Edge

Edge functions running the Vercel AI SDK demand fast execution and zero bloat. By combining the SDK with this endpoint, you can fetch Jasper style guidelines using `get_style` and inject them straight into your prompt context. You don't have to hardcode Jasper style rules in your React app. Just call `list_voices` to select a specific voice ID, then pass it to `run_command` to keep all streaming content consistent with your brand guidelines.

Ground LLM responses with real-time knowledge

Avoid hallucinations in your Next.js app by grounding the generation process with this MCP connection. The Vercel AI SDK can run `search_knowledge` to find relevant Jasper context items, then feed those details directly into the generation prompt. If you need to verify specific details, `get_knowledge_item` retrieves the raw text. This lets your Vercel AI SDK setup construct highly accurate prompts based on your actual company data stored in Jasper.

Setup guide

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

You initialize the client using createMCPClient and pass the server tools to streamText. From there, calling `run_template` streams the content block-by-block directly to your React frontend.

Yes. You can call `list_voices` and `get_voice` within your Edge runtime to fetch brand profiles. This lets you apply those profiles to your generation calls without adding latency.

The server handles the core API authentication on Vinkius. You just configure createMCPClient with your Vinkius token, and the SDK handles the tool execution securely.

No. You call `get_template` to fetch the input schema, then pass those exact fields as JSON parameters to `run_template`.

All style guides and voice profiles retrieved via `list_styles` and `get_voice` run in an isolated V8 sandbox on Vinkius. Your brand assets are never cached, stored, or used for model training.

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