How to Use the Bot9 MCP in Vercel AI SDK

Q: How do I stream Bot9 conversation histories in Vercel AI SDK?

Install the packages using npm install ai @ai-sdk/mcp and instantiate the client using createMCPClient. Pass the getconversationhistory tool directly to streamText and always call mcpClient.close() when finished.

Q: Can I train a new chatbot using Bot9 and Vercel AI SDK?

Yes. Pass the adddatasource tool into your Vercel AI SDK tool configuration array, allowing your agent to ingest new training URLs on demand.

Q: How does the Bot9 MCP Server handle active support sessions?

It exposes listconversations and sendmessage as executable tools. Your AI client calls these to monitor chats and shoot replies back to users without manual intervention.

Stream Bot9 customer support chat logs and bot training directly into your React app 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 Bot9 MCP to Vercel AI SDK

Create your Vinkius account to connect Bot9 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 Bot9 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Bot9 Training in Vercel AI SDK UI

Feed raw documentation URLs directly into your Bot9 support bots from your Next.js frontend using `add_data_source`. Your Vercel AI SDK agent can check existing documents via `list_data_sources` to prevent duplicate training runs. By feeding these Bot9 MCP tools directly to `streamText`, the Vercel AI SDK renders the training status instantly on the screen. Your users get immediate visual confirmation that their chatbot is learning without waiting for a full Vercel AI SDK page reload.

Programmatic Fleet Deployment for Next.js

Spin up new Bot9 customer service agents programmatically using `create_bot` and track their active sessions using `list_bots` inside your Next.js API routes with Vercel AI SDK. This setup bypasses manual dashboards, letting your Vercel AI SDK application manage your entire Bot9 support fleet dynamically. The Vercel AI SDK handles these Bot9 tool calls at the edge, meaning you can spin up a localized support bot instantly. Your React components receive the fresh Bot9 configuration from `get_bot` as soon as the Vercel AI SDK edge function executes.

Direct Conversation Streaming

Pull active Bot9 chat logs using `get_conversation_history` and push new replies with `send_message` inside your Vercel AI SDK chat window. This lets your Vercel AI SDK frontend display live Bot9 agent conversations as they happen, giving your team immediate eyes on customer issues. Integrating this Bot9 MCP Server with Vercel AI SDK's `streamText` ensures that every customer response streams token-by-token. Your Next.js UI updates the active Bot9 session list with `list_conversations` behind the scenes using Vercel AI SDK.

Setup guide

Set up Bot9 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 Bot9 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 Bot9 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 Bot9. 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 Bot9 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 Bot9 MCP in Vercel AI SDK

Install the packages using `npm install ai @ai-sdk/mcp` and instantiate the client using `createMCPClient`. Pass the `get_conversation_history` tool directly to `streamText` and always call `mcpClient.close()` when finished.

Yes. Pass the `add_data_source` tool into your Vercel AI SDK tool configuration array, allowing your agent to ingest new training URLs on demand.

It exposes `list_conversations` and `send_message` as executable tools. Your AI client calls these to monitor chats and shoot replies back to users without manual intervention.

No, Vinkius handles the credentials for you. Simply pass your single endpoint token through the MCP client's authProvider to start calling tools securely.

Yes. This integration handles sensitive chat messages, bot settings, and knowledge base URLs. Vinkius processes all tool interactions inside isolated V8 sandboxes, meaning your conversation logs are never stored or exposed to third parties.

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