How to Use the Bidsketch MCP in Vercel AI SDK

Q: How do I hook up the Bidsketch MCP Server to Vercel AI SDK?

Install the required packages and call createMCPClient with your Vinkius URL. Pass the resulting tools directly into streamText to let your agent call them.

Q: How does Vercel AI SDK handle Bidsketch template selection?

Your agent calls listtemplates to get your layout IDs first. It then injects the chosen template ID into the createproposal payload to generate the correct document.

Q: Can I build a custom dashboard with this setup?

Yes. You use listproposals to feed real-time pipeline metrics directly into your React components without writing custom backend controllers.

Watch Bidsketch proposal statuses and client creation feed directly into your React frontend in real-time 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 Bidsketch MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live Bidsketch proposals in Vercel AI SDK

The `list_proposals` tool pulls your sales pipeline data directly into your frontend without loading spinners. By feeding this tool into the streaming text generator, your users watch proposal names, values, and statuses render line-by-line as your agent processes them. This direct connection means your Edge Functions do not block while waiting for a complete API payload. You can call `get_proposal_details` to fetch specific terms, rendering the exact contract structure live in your user interface.

Fast client onboarding via MCP Server

The `create_client` tool lets your agent register new leads in your sales pipeline on the fly. Instead of writing custom API wrappers, you pass this tool to your Vercel AI SDK setup to handle registration during a chat session. To keep your contact list clean, the agent uses `list_clients` first to check for duplicates. If no match exists, it fires the creation tool and updates your UI state immediately.

Generate and send draft proposals instantly

The `create_proposal` tool builds structured estimates by feeding raw JSON data directly to your Bidsketch account. Your application uses `list_templates` to fetch your pre-approved layouts, ensuring every generated offer matches your brand guidelines. Once the template is selected, the SDK streams the proposal creation progress to the user. This setup turns raw user input into a sent proposal in under five seconds.

Setup guide

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

Install the required packages and call `createMCPClient` with your Vinkius URL. Pass the resulting tools directly into `streamText` to let your agent call them.

Yes, the Vinkius endpoint runs on a V8 sandbox that works with Edge runtimes. You avoid large SDK footprints by using the lightweight MCP client protocol.

Your agent calls `list_templates` to get your layout IDs first. It then injects the chosen template ID into the `create_proposal` payload to generate the correct document.

Yes. You use `list_proposals` to feed real-time pipeline metrics directly into your React components without writing custom backend controllers.

Your client emails and contract values never touch third-party servers. Vinkius runs your integrations inside isolated, ephemeral V8 sandboxes that wipe all memory immediately after your API call finishes.

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