How to Use the Bland AI MCP in Vercel AI SDK

Q: How do I configure Bland AI call triggers in Vercel AI SDK?

You pass the Bland AI tools to streamText or generateText after initializing the Vercel AI SDK client. Call sendphonecall to initiate the outbound Bland AI dialer directly from your Vercel serverless route.

Q: Can Vercel AI SDK handle live transcript analysis from Bland AI?

Yes, by calling analyzecalltranscript within your Vercel AI SDK streaming function. The Vercel AI SDK streams the resulting Bland AI post-call analysis directly to your React components.

Q: How do I manage Bland AI voice agents using Vercel AI SDK?

You run createvoiceagent or updateagentconfig inside your Vercel edge functions. The Vercel AI SDK treats these Bland AI configurations as standard tool calls, returning the updated parameters to your React state.

Q: How do I clean up the Vercel AI SDK connection after a Bland AI call?

Always call mcpClient.close() once your Vercel edge function completes its Bland AI session. This prevents hanging HTTP connections and ensures your Vercel serverless environment scales efficiently during high call volumes.

Trigger Bland AI voice agents and stream live phone call data directly to your Next.js app with 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 Bland AI MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live voice agent deployment via Vercel AI SDK

Your Next.js app can now deploy Bland AI voice agents on the fly using Vercel AI SDK. By passing `create_voice_agent` and `list_available_voices` to your Vercel AI SDK MCP setup, you let React users spin up phone representatives instantly. The Vercel AI SDK pulls Bland AI voice options instantly to render them in your frontend. Users configure their phone agent's script and watch the Bland AI settings update in real-time on their Vercel dashboard.

Stream live call transcripts to your frontend UI

Stop making users wait for a loading spinner when Vercel AI SDK fetches Bland AI call logs. This integration lets you pull live data using `get_call_details` and `analyze_call_transcript` to show React users exactly what happened on the Bland AI call. Handling this data stream at the edge prevents slow loading times. Your React UI updates line-by-line as the Vercel AI SDK summarizes the Bland AI call transcript.

Active call control from edge functions

Developers can execute real-time call interruptions on Bland AI lines using this MCP Server directly from Vercel edge functions. When a user clicks a button in your React interface, your Vercel AI SDK agent triggers `stop_active_call` to cut the Bland AI line instantly. You manage active Bland AI sessions using `list_recent_calls` in your Vercel client. This gives your Next.js UI a real-time monitor of every outbound Bland AI call your system makes.

Setup guide

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

You pass the Bland AI tools to `streamText` or `generateText` after initializing the Vercel AI SDK client. Call `send_phone_call` to initiate the outbound Bland AI dialer directly from your Vercel serverless route.

Yes, by calling `analyze_call_transcript` within your Vercel AI SDK streaming function. The Vercel AI SDK streams the resulting Bland AI post-call analysis directly to your React components.

You run `create_voice_agent` or `update_agent_config` inside your Vercel edge functions. The Vercel AI SDK treats these Bland AI configurations as standard tool calls, returning the updated parameters to your React state.

Always call `mcpClient.close()` once your Vercel edge function completes its Bland AI session. This prevents hanging HTTP connections and ensures your Vercel serverless environment scales efficiently during high call volumes.

Your Bland AI phone call transcripts and voice configurations remain secure within the Vinkius MCP Server sandbox during Vercel AI SDK execution. We never log the content of your conversations or store agent configuration scripts on our servers.

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