How to Use the Freshsales MCP in Vercel AI SDK

Q: How do I connect the Vercel AI SDK to Freshsales?

Run npm install ai @ai-sdk/mcp in your project. Set up the connection using createMCPClient with your HTTP endpoint, then pass the tools directly to streamText. Always call mcpClient.close() when the session ends.

Q: Can Vercel AI SDK create new leads in Freshsales?

Yes. Your agent calls the createlead tool during a conversation and pushes the data to the CRM. The only required field is the prospect's last name.

Build live sales dashboards in React or Next.js by streaming Freshsales data directly to users with 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 Freshsales MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Freshsales MCP Server Data Live

The `create_lead` tool lets your Vercel AI SDK app push new prospects straight into your CRM from a user-facing chat interface. You only need a last name to fire the request, though adding an email builds a better profile. Instead of making users wait for a backend sync, the AI streams the confirmation back to the UI instantly. Reading existing data works the same way. When a user asks about a prospect, your agent calls `get_lead` and renders the details into your Next.js frontend component piece by piece. The end user sees the information appear in real-time.

Render Deal Pipelines in React

The `list_deals` tool pulls active sales opportunities out of the CRM so your frontend can display them dynamically. You can hook this into a custom Vue or Svelte dashboard where the AI reads the current pipeline state on load. Combine this with `list_appointments` to show reps exactly what they need to do today. The agent fetches the schedule and streams the output directly into a calendar component. Nobody stares at a loading spinner while the app figures out the day's agenda.

Browse Sales Accounts Instantly

The `list_sales_accounts` tool gives your application immediate access to company profiles stored in the CRM. If a rep searches for an account in your custom UI, the AI queries the database and streams the company details back. Digging deeper requires the `list_contacts` and `get_contact` tools. Your agent pulls the specific people associated with those accounts and displays their contact info. It turns a static AI chat into a live, interactive sales directory.

Setup guide

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

Run `npm install ai @ai-sdk/mcp` in your project. Set up the connection using `createMCPClient` with your HTTP endpoint, then pass the tools directly to `streamText`. Always call `mcpClient.close()` when the session ends.

Yes. Your agent calls the `create_lead` tool during a conversation and pushes the data to the CRM. The only required field is the prospect's last name.

The integration works perfectly on the Edge. You can deploy your Next.js app globally and stream CRM data like `list_tasks` without cold boot delays.

Waiting creates a terrible user experience. Streaming the output of `list_notes` or `list_deals` means the user starts reading the CRM data immediately while the rest of the response finishes generating.

Your Vinkius endpoint token secures the connection between the application and the CRM. When the AI pulls sensitive information via `get_contact` or `list_leads`, that data travels through an ephemeral V8 Isolate Sandbox. The server forgets everything the exact millisecond the request completes.

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