How to Use the Freshchat MCP in Vercel AI SDK

Q: How do I stream Freshchat messages using Vercel AI SDK?

Install the @ai-sdk/mcp package to connect Vercel AI SDK with Freshchat. Pass the listchatmessages tool directly to streamText to pipe real-time conversation histories straight to your frontend.

Q: How does the Freshchat client for Vercel AI SDK handle agent assignment updates?

The MCP Server exposes listsupportagents to your Vercel AI SDK codebase. Your streaming client reads this Freshchat metadata to determine which agents are active and updates the UI state immediately.

Stream Freshchat support tickets and live agent updates directly to your frontend using 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 Freshchat MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time chat feeds in Vercel AI SDK

Stop making users wait for REST requests to resolve when displaying Freshchat threads in your Vercel AI SDK application. This MCP Server lets your application stream raw Freshchat customer interactions directly into your React or Next.js components. By calling `list_chat_messages` and `list_conversations`, your Vercel AI SDK interface updates instantly as new Freshchat support queries land in your dashboard. You do not need complex polling setups on your frontend to display Freshchat status updates. The Vercel AI SDK handles the streaming connection, pulling live records via `get_conversation_details` so your users see the exact status of their support tickets without hitting a refresh button.

Instant customer lookup during live sessions

When a user initiates a Freshchat session, your Vercel AI SDK interface needs their history immediately. Your Vercel AI SDK agent uses `search_chat_users` to find matching emails and pull profiles before the user even types their first question. This MCP Server fetches Freshchat context using `get_chat_user_details` to feed the active Vercel AI SDK session. This means your Vercel AI SDK UI displays previous touchpoints and account tiers immediately, giving your automated agents the data they need to respond accurately.

Dynamic agent routing and assignment

Routing tickets shouldn't happen in a black box when managing Freshchat inside Vercel AI SDK. This MCP Server displays available support staff by executing `list_support_agents` and showing their group assignments in real-time. The Vercel AI SDK agent checks team availability through `list_agent_groups` and immediately updates the UI. This lets your Vercel AI SDK frontend dynamically show which human teams are online in Freshchat to take over high-priority escalations.

Setup guide

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

Install the `@ai-sdk/mcp` package to connect Vercel AI SDK with Freshchat. Pass the `list_chat_messages` tool directly to `streamText` to pipe real-time conversation histories straight to your frontend.

Yes, this setup is fully compatible with Edge runtimes when querying Freshchat. Your Vercel AI SDK agent can run `search_chat_users` globally with minimal latency, keeping your serverless functions fast and responsive.

The MCP Server exposes `list_support_agents` to your Vercel AI SDK codebase. Your streaming client reads this Freshchat metadata to determine which agents are active and updates the UI state immediately.

No, you do not need custom code to bridge Freshchat and Vercel AI SDK. The MCP Server exposes pre-configured tools like `send_chat_message` and `get_conversation_details` directly to your model, removing the need for manual endpoint mapping.

Your sensitive Freshchat chat messages and agent profiles never touch public servers. Vinkius runs this connector inside a secure, zero-trust sandbox, passing data directly between your local Vercel AI SDK runtime and the target platform.

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