How to Use the Twilio SendGrid MCP in Vercel AI SDK
Real-time communication workflows built for the Vercel AI SDK.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Twilio SendGrid MCP to Vercel AI SDK
Create your Vinkius account to connect Twilio SendGrid 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.
Stream Live Email Responses into Your UI
When you use `dispatch_email`, your agent sends HTML emails using SendGrid's SMTP relay. The results stream directly to the user interface, so they see the action happen live in real time. This is perfect for building interactive products where users need instant feedback on communication tasks.
Manage Contacts and Lists with Confidence
Need a contact profile? Call `search_contact_by_email` to get everything—custom fields, list memberships, segments—for any marketing contact. You can also use `list_marketing_contacts` or `list_marketing_lists` to prep your data before sending.
Maintain Clean Suppression Lists
Don't let bad data damage reputation. Use `delete_bounce` to remove an email from the bounce suppression list, keeping your sender score clean. Similarly, you can run `delete_spam_report` if a user was accidentally flagged for spam.
Set up Twilio SendGrid MCP in Vercel AI SDK
Prerequisites
- Node.js 18+ and a TypeScript project
-
ai+@modelcontextprotocol/sdkpackages - Active Vinkius subscription with a valid endpoint token
- 1
Install dependencies
Run
npm install ai @modelcontextprotocol/sdkplus your preferred model provider (e.g.@ai-sdk/openai). - 2
Create the Streamable HTTP transport
Use
StreamableHTTPClientTransportwith 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 Twilio SendGrid tools. Pass them directly togenerateText()orstreamText()— 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.
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 Twilio SendGrid transactions",
});
console.log(text);
await mcpClient.close(); Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Twilio SendGrid. 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.
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 Twilio SendGrid MCP in Vercel AI SDK
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Twilio SendGrid MCP today
We host it, we monitor it, we maintain it. You just paste one token.