How to Use the Clearstory MCP in Vercel AI SDK

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

Install @ai-sdk/mcp and initialize your client with createMCPClient. Point the HTTP transport URL to your Vinkius endpoint, then pass the returned tools to streamText.

Q: Can Vercel AI SDK stream Clearstory change order details?

Yes. The integration supports streaming the output of getcordetails straight to your frontend components. Users see the financial breakdowns appear character by character.

Stream construction change orders directly into your React UI with the Clearstory MCP Server integration for 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 Clearstory MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live Dashboards with Vercel AI SDK

Your users hate waiting for spinners to finish loading project data, which is why calling `list_construction_projects` streams active job sites straight into your Next.js frontend. The model processes the construction records and pipes them to the client before the full response even finishes generating. It gets better when contractors submit new rates. You can trigger `list_construction_rates` and render Labor, Material, and Equipment numbers in real-time. The end user watches the financial grid populate instantly.

Surface Change Order Requests instantly

Tracking down pending approvals normally requires digging through endless menus until your custom chat interface calls `list_change_order_requests`. The pending approvals appear right in the conversation window. Your project managers stop hunting for documents and start making decisions. If a superintendent needs specifics, the model hits `get_cor_details`. You get the exact dollar amounts and justifications streaming back to the client while the user reads the first sentence.

Render T&M tags on the edge

Field crews submit Time & Material tags constantly, making `list_tm_tags` perfect for an Edge Function that catches updates without hitting a heavy backend server. You keep your architecture lightweight while maintaining a direct pipe to the job site. Connect this to `list_change_notifications` to build a live feed of contractor communications. It turns a static portal into an active, breathing view of project finances.

Setup guide

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

Install `@ai-sdk/mcp` and initialize your client with `createMCPClient`. Point the HTTP transport URL to your Vinkius endpoint, then pass the returned tools to `streamText`.

Yes. The integration supports streaming the output of `get_cor_details` straight to your frontend components. Users see the financial breakdowns appear character by character.

It runs perfectly on the edge. You just need to ensure you call `mcpClient.close()` when the serverless execution finishes to prevent hanging connections.

Pass your search parameters through the prompt. The model will automatically map those constraints to the arguments for `list_construction_projects` before executing the tool call.

Vinkius runs your connection inside an ephemeral V8 Isolate Sandbox. Your labor rates and unapproved change orders stay completely isolated. The moment the session ends, the environment is destroyed.

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