How to Use the Convoy MCP in Vercel AI SDK

Q: How do I connect the Convoy MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and ai via npm. Use createMCPClient to connect to the Vinkius endpoint, then pass the tools array from mcpClient.tools() into generateText or streamText. Remember to call mcpClient.close() when the execution finishes.

Push real-time webhook delivery updates straight to your Next.js frontend with Convoy and 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 Convoy MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Webhook Monitoring in Vercel AI SDK

Your users do not want to reload a dashboard to see if an API call succeeded. When you hook this MCP Server to your Vercel AI SDK setup, your agent can pull delivery logs using `list_delivery_attempts` and stream the status directly to the UI. The user watches the agent fetch and parse the logs in real time. If a payload fails, the agent does not just report the error. It uses `get_delivery_attempt` to inspect the exact failure reason and streams the raw response body onto the page. Your frontend displays this data instantly while the Edge Function keeps running.

Instant Endpoint Control on the Edge

Managing destinations should not require custom API wrappers in your Next.js routes. Your agent uses `create_endpoint` to register new URLs on the fly, directly responding to user prompts in your chat interface. The Vercel AI SDK handles the tool call execution, and the agent confirms the new endpoint is active. When an endpoint acts up, the agent can run `pause_endpoint` to stop the bleeding, then switch it back on with `activate_endpoint` once the user confirms their server is back up. This turns your chat UI into a live control plane for webhook routing.

Direct Subscription Filtering from Chat

Let users filter their incoming events without clicking through complex setting pages. The agent calls `create_subscription` to bind events to specific destinations based on the conversation context. You pass these tools directly into `streamText` to let the agent handle the configuration logic. To make it faster, the agent uses `bulk_create_filters` to apply multiple rules at once. The user simply types what they want to receive, and the Vercel AI SDK executes the tool to update the Convoy routing rules instantly.

Setup guide

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

Install `@ai-sdk/mcp` and `ai` via npm. Use `createMCPClient` to connect to the Vinkius endpoint, then pass the tools array from `mcpClient.tools()` into `generateText` or `streamText`. Remember to call `mcpClient.close()` when the execution finishes.

Yes. The Vinkius hosted MCP endpoint runs over HTTP, making it fully compatible with Vercel's Edge runtime. Your agent can call `broadcast_event` or `list_endpoints` without cold-start delays or node-specific dependencies.

Vinkius manages the core credentials for the MCP Server, so you only need one endpoint token. For dynamic user authentication, you can pass an `authProvider` to the `createMCPClient` config to scope calls like `create_portal_link` to specific user accounts.

You should configure the tool execution timeout in your Vercel AI SDK settings. If a call to `batch_retry_event_deliveries` takes too long, the SDK handles the rejection gracefully, allowing your agent to explain the delay to the user.

Vinkius runs the server in an isolated V8 sandbox, meaning webhook payloads and endpoint URLs never persist on our servers. The raw JSON payloads processed by `create_event` are encrypted in transit and only touch ephemeral memory during the tool execution.

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