How to Use the FastGPT MCP in Vercel AI SDK

Q: How do I handle streaming tool calls with FastGPT and Vercel AI SDK?

Use createMCPClient to connect to the MCP server and pass the tools directly to streamText. When the agent triggers chatcompletions, the SDK streams the token output and intermediate steps directly to your React components.

Q: How do I clean up connections after querying datasets?

Always call mcpClient.close() once your stream finishes. This prevents connection leaks in your serverless functions when running operations like listdatasets.

Feed FastGPT knowledge bases directly into your Vercel AI SDK stream to render raw data live on the edge without 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 FastGPT MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live FastGPT search results to Vercel AI SDK UI

The `search_dataset_data` tool streams vector data directly to your edge runtime to eliminate user-facing spinners. This MCP server lets your edge runtime call the database and stream matching chunks directly to the browser. By feeding the results into `streamText`, the Vercel AI SDK renders incoming knowledge base hits as they arrive. Users see the exact source context surfacing in real-time.

Manage knowledge bases on the edge

The `create_dataset` and `push_dataset_data` tools let you build user-facing dashboards where clients upload docs directly. You don't need complex backend setups to handle ingestion. The Vercel AI SDK handles the tool execution loop, letting your frontend trigger background dataset updates without blocking the main chat thread.

Keep chat context synced across sessions

The `chat_completions` tool tracks conversational context across sessions by passing a persistent `chatId`. This MCP setup binds the Vercel AI SDK's active message history directly to FastGPT's app memory. You don't have to manually manage session states or sync arrays. The server handles the mapping so your agent stays on track.

Setup guide

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

Use `createMCPClient` to connect to the MCP server and pass the tools directly to `streamText`. When the agent triggers `chat_completions`, the SDK streams the token output and intermediate steps directly to your React components.

Yes. Because the MCP client uses standard HTTP MCP transport, you can call `push_dataset_data` or `update_dataset_data` directly inside Next.js edge routes without hitting Node.js runtime limits.

This MCP server abstracts the API payload structure into clean, typed schemas. Instead of manually writing fetch requests for `search_dataset_data`, you let the SDK call the tool dynamically based on user intent.

Always call `mcpClient.close()` once your stream finishes. This prevents connection leaks in your serverless functions when running operations like `list_datasets`.

Your data runs through secure V8 isolates on Vinkius, meaning your raw text documents and vector embeddings are never written to persistent disk during transit. The server acts as a pass-through, sending payloads directly to your FastGPT instance over encrypted channels.

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