How to Use the Copilot CRM (Assembly) MCP in Vercel AI SDK

Q: How do I stream Copilot CRM (Assembly) portal files to a Vercel AI SDK frontend?

You use the listfiles tool within your streaming text function. Call mcpClient.tools() to grab the server tools, pass them to streamText, and render the file metadata directly in your React components as the chunked data arrives.

Q: How do I handle custom fields in my Next.js client portal?

You query listcustomfields first. This gives your agent the exact keys needed to parse or update records via updateclient without breaking your database constraints.

Build Next.js frontends where your AI SDK agent streams live Copilot CRM (Assembly) data straight to your users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Copilot CRM (Assembly) MCP to Vercel AI SDK

Create your Vinkius account to connect Copilot CRM (Assembly) 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 Copilot CRM (Assembly) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time client onboarding with Vercel AI SDK

The `create_client` tool lets your Vercel AI SDK app register new portal users on the fly. Instead of making users wait for a full page reload, the agent spins up the profile and streams the confirmation state directly into your React components. You can immediately follow up by calling `update_client` to link company records or set custom properties. Because this runs on edge-compatible infrastructure, your users get instant feedback without server-side lag.

Live invoice and portal file rendering

This MCP Server exposes `list_invoices` and `list_files` so your streaming chat interface can display billing documents and portal uploads instantly. Your Vercel AI SDK frontend doesn't need to poll an external API; the agent fetches the metadata and renders it as it arrives. Users can ask "what bills are due?" and see a live-rendered list pop up in their chat window. The UI updates dynamically as the JSON payload streams in, bypassing slow loading spinners entirely.

Dynamic custom field lookup in the UI

We use the `list_custom_fields` tool to let your Vercel AI SDK agent discover how your specific portal is configured. This lets the LLM map user inputs to your exact database schema without hardcoded field IDs in your frontend code. Once the schema is resolved, the agent can fetch detailed profiles using `get_client_details`. The entire interaction stays fluid and responsive, keeping the user experience snappy.

Setup guide

Set up Copilot CRM (Assembly) 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 Copilot CRM (Assembly) 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 Copilot CRM (Assembly) 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 Copilot CRM. 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 Copilot CRM (Assembly) 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 Copilot CRM (Assembly) MCP in Vercel AI SDK

You use the `list_files` tool within your streaming text function. Call `mcpClient.tools()` to grab the server tools, pass them to `streamText`, and render the file metadata directly in your React components as the chunked data arrives.

Yes. The server is fully compatible with Edge runtimes, meaning your Vercel AI SDK agent can run `update_client` requests with minimal latency. Just configure the HTTP transport in your Edge route handler.

Absolutely, you can intercept the tool call before execution. When the agent attempts to run `create_client`, your frontend can pause the stream, prompt the user for confirmation, and then resume the operation.

You query `list_custom_fields` first. This gives your agent the exact keys needed to parse or update records via `update_client` without breaking your database constraints.

Your invoice records and client identities never touch public logs. Vinkius runs this server inside an isolated, zero-trust V8 sandbox, ensuring that sensitive financial data retrieved via `list_invoices` stays strictly between your SDK client and the portal.

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