How to Use the Freshsales (Sales CRM & Lead Scoring API) MCP in Vercel AI SDK

Q: How do I run the Freshsales (Sales CRM & Lead Scoring API) tools inside a Vercel AI SDK Edge Function?

You import the MCP client from @ai-sdk/mcp and initialize it with your Vinkius endpoint. Pass the tools directly to streamText to let your LLM run createlead or updatecontact with minimal latency on the edge.

Q: How do I manage API rate limits when connecting Vercel AI SDK to the Freshsales (Sales CRM & Lead Scoring API)?

You should cache responses from static endpoints like listdealstages or listleadsources. This prevents your edge functions from hitting the API limits during high-traffic user sessions.

Q: What happens if a mandatory field is missing when creating a lead?

The createlead tool requires at least a first name or email. If the model fails to extract these from the chat, the SDK catches the API error, allowing your application to prompt the user for the missing details.

Feed live CRM updates directly into your React or Next.js app with this Freshsales (Sales CRM & Lead Scoring API) Vercel AI SDK MCP integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsales (Sales CRM & Lead Scoring API) MCP to Vercel AI SDK

Create your Vinkius account to connect Freshsales (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time pipeline UI updates

The `list_leads` tool pulls raw prospect records directly into your Next.js edge functions. Your Vercel AI SDK client renders the incoming pipeline data live as it arrives from the CRM, skipping the usual blank loading states that kill user engagement. If you need to qualify a prospect immediately, the `convert_lead` tool triggers the conversion on the backend while streaming the new contact object to the frontend. This setup cuts down on manual page refreshes because the UI displays the updated state the millisecond the API responds.

Direct lead generation from interactive forms

The `create_lead` tool handles incoming form submissions by routing them directly into your Freshsales database. By passing this tool to `streamText`, your Vercel AI SDK setup can capture user intent during a chat session and instantly build a clean profile. When the contact is saved, you can immediately run `create_task` to assign a follow-up action to a sales rep. This keeps your data clean and ensures no hot lead sits in limbo waiting for a manual batch export.

Interactive deal creation with Vercel AI SDK MCP Server

The `create_deal` tool lets you spin up new sales opportunities directly inside the chat interface. Instead of forcing reps to open a separate browser tab to log a sale, the Vercel AI SDK calls the endpoint and displays the new deal stage in real-time. You can also pull the exact pipeline architecture using `list_deal_stages` to populate dropdowns dynamically. This guarantees that every deal created by your application matches your actual sales pipeline stages without hardcoded values.

Setup guide

Set up Freshsales (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) 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 (Sales CRM & Lead Scoring API) MCP in Vercel AI SDK

You import the MCP client from `@ai-sdk/mcp` and initialize it with your Vinkius endpoint. Pass the tools directly to `streamText` to let your LLM run `create_lead` or `update_contact` with minimal latency on the edge.

Yes, the SDK streams the tool execution step dynamically. When the model invokes `convert_lead`, the UI updates progressively while the backend processes the mandatory company and last name fields.

You should cache responses from static endpoints like `list_deal_stages` or `list_lead_sources`. This prevents your edge functions from hitting the API limits during high-traffic user sessions.

The `create_lead` tool requires at least a first name or email. If the model fails to extract these from the chat, the SDK catches the API error, allowing your application to prompt the user for the missing details.

Vinkius runs this server in an isolated V8 sandbox, meaning your raw lead details, deal values, and private notes never persist on external disks. All traffic to the API is encrypted, keeping your sales pipeline data completely isolated from other tenants.

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