How to Use the CRM PipeRun MCP in Vercel AI SDK

Q: Can the Vercel AI SDK handle base64 encoding for CRM PipeRun files?

Yes. When triggering the uploadfile tool, your frontend reads the file as base64 and passes the raw string through the SDK client to the PipeRun API.

Stream CRM PipeRun activity updates and file uploads directly to your web app 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 CRM PipeRun MCP to Vercel AI SDK

Create your Vinkius account to connect CRM PipeRun 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 CRM PipeRun with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed PipeRun tasks directly into your AI SDK interface

This MCP Server exposes `list_activities` and `update_activity` to let your users view and edit sales tasks without waiting for page reloads. By binding these tools to your frontend agent, the Vercel AI SDK streams live pipeline updates straight to the browser. When a sales rep finishes a call, the agent updates the status instantly. They watch the task change in real-time because the JSON payload streams directly into your React or Next.js components.

Upload deal files live via the Vercel AI SDK

The `upload_file` tool handles document uploads instantly when a user drags a contract into your chat component. The SDK handles the base64 encoding behind the scenes, pushing the document directly to the relevant PipeRun deal or company. If a rep needs to verify what's already uploaded, the agent calls `list_files` to populate a live sidebar list. No loading spinners or stale data, just immediate feedback in your edge-rendered web application.

Schedule sales follow-ups using this MCP Server

The `list_activity_types` tool queries your current setup so your AI client can handle calendar logistics. It schedules the next step using `create_activity` based on user input. Because this MCP Server runs on Vinkius, your Edge Functions stay fast and light. The Vercel AI SDK processes these tool calls over a lightweight SSE transport, keeping your serverless execution times low.

Setup guide

Set up CRM PipeRun 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 CRM PipeRun 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 CRM PipeRun 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 PipeRun. 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 CRM PipeRun 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 CRM PipeRun MCP in Vercel AI SDK

Install the Vercel AI SDK MCP package and initialize it with your Vinkius endpoint using createMCPClient. Pass the tools directly into streamText to let your agent manage your sales activities.

Yes. When triggering the upload_file tool, your frontend reads the file as base64 and passes the raw string through the SDK client to the PipeRun API.

The Vinkius infrastructure buffers incoming requests safely. You should still implement standard error boundaries in your Next.js or React code to catch any API exceptions.

No. Vinkius handles the authorization layer on its secure servers, so your frontend code only requires the single endpoint token.

Yes, security is handled at the transport layer. Your sales documents, tasks, and company attachments pass through ephemeral V8 isolates, meaning no data is stored on Vinkius servers or exposed to public networks.

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