How to Use the CrewAI Platform MCP in Vercel AI SDK

Q: How do I authenticate the CrewAI Platform MCP Server in Vercel AI SDK?

You pass your Vinkius access token when setting up createMCPClient. If you need user-specific authentication, configure the authProvider block to inject OAuth headers dynamically before calling mcpClient.tools().

Q: Can I stream output from CrewAI Platform runs using Vercel AI SDK?

Streaming the tool outputs directly into streamText is fully supported. When the agent runs kickoffcrew, the resulting JSON payload streams straight to the frontend, allowing your UI to render the agent actions as they happen.

Q: How do I clean up the MCP connection after running a crew kickoff?

Always call mcpClient.close() once your execution finishes. This prevents lingering connections in your serverless environments and keeps your Vercel function executions clean and fast.

Q: How does the server handle my agent billing data and webhook arrays?

Vinkius processes all tool calls like getagent and listwebhooks in isolated V8 sandboxes. Your sensitive billing rules and webhook payloads are never stored on our servers; they transit through an ephemeral, zero-trust network that destroys the execution context the moment the tool returns its output.

Pipe live multi-agent crew execution data straight into your React components using 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 CrewAI Platform MCP to Vercel AI SDK

Create your Vinkius account to connect CrewAI Platform 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 CrewAI Platform with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track CrewAI Platform runs live in Vercel AI SDK

This MCP Server lets your Vercel AI SDK app query CrewAI Platform execution logs on the fly. By calling `get_run_status`, your Vercel AI SDK application pulls live execution telemetry directly from the CrewAI Platform without making users stare at a blank screen. You can feed these metrics right into `streamText` to render progress bars as CrewAI Platform tasks execute. If a run stalls, use `cancel_run` to kill the process and free up your Vercel AI SDK backend resources instantly.

Read active crew structures inside Edge Functions

Fetching active CrewAI Platform setups requires zero heavy database queries when you use this Vercel AI SDK integration. Your Vercel AI SDK agent invokes `get_crew` to pull the active properties driving your CrewAI Platform account logic. The `get_agent` tool pulls down specific billing rules and structured definitions directly into your Vercel AI SDK frontend state. Because the Vercel AI SDK client is lightweight, you can run this entire CrewAI Platform discovery flow inside Edge Functions without hitting cold start delays.

Audit active queues on the client side

Checking CrewAI Platform task queues shouldn't require writing complex API wrappers in your Vercel AI SDK codebase. Your Vercel AI SDK code calls `list_tasks` to pull CrewAI Platform gateway history, feeding the raw output to your components. To keep your Vercel AI SDK UI in sync with external events, call `list_webhooks` to inspect native CrewAI Platform hold parsing arrays. This ensures your customer-facing dashboard always reflects the current CrewAI Platform state in real-time.

Setup guide

Set up CrewAI Platform 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 CrewAI Platform 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 CrewAI Platform 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 CrewAI. 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 CrewAI Platform 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 CrewAI Platform MCP in Vercel AI SDK

You pass your Vinkius access token when setting up `createMCPClient`. If you need user-specific authentication, configure the `authProvider` block to inject OAuth headers dynamically before calling `mcpClient.tools()`.

Streaming the tool outputs directly into `streamText` is fully supported. When the agent runs `kickoff_crew`, the resulting JSON payload streams straight to the frontend, allowing your UI to render the agent actions as they happen.

Standard REST requests force you to write complex state management and parsing code. This server exposes actions like `list_agents` and `get_task` as native tools that your Vercel AI SDK agent calls automatically based on user prompts.

Always call `mcpClient.close()` once your execution finishes. This prevents lingering connections in your serverless environments and keeps your Vercel function executions clean and fast.

Vinkius processes all tool calls like `get_agent` and `list_webhooks` in isolated V8 sandboxes. Your sensitive billing rules and webhook payloads are never stored on our servers; they transit through an ephemeral, zero-trust network that destroys the execution context the moment the tool returns its output.

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