How to Use the Freshsuccess MCP in Mastra AI

Q: How do I register Freshsuccess tools in Mastra AI?

Instantiate a new MCPClient and map the endpoint URL in the servers object. Call mcpClient.listTools() and spread the output into your Agent's tool array.

Q: Can Mastra AI automatically retry failed Freshsuccess API calls?

Yes. If checkapistatus fails or a metric update times out, the workflow engine catches the error. It applies exponential backoff and attempts the connection again.

Q: How do I build a churn response workflow with Mastra AI and Freshsuccess?

Create a workflow that triggers listcsalerts daily. Use a conditional branch to check the alert type. If it flags a usage drop, route the agent to call listcstasks and assign a follow-up.

Q: Does the MCP Server support Mastra's human-in-the-loop features?

It does. You flag specific tools like upsertcsaccount to require human approval before execution. The workflow suspends until a manager signs off on the CRM update.

Build conditional customer success workflows that react to Freshsuccess churn alerts using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsuccess MCP to Mastra AI

Create your Vinkius account to connect Freshsuccess to Mastra AI 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 Freshsuccess with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route Freshsuccess Alerts with Mastra AI

High-value accounts rarely churn without warning. By connecting the Freshsuccess MCP Server to Mastra AI, you build workflows that catch these warnings early. Your agent polls `list_cs_alerts` and evaluates the severity of each drop in usage. This is where conditional branching takes over. If the alert indicates critical health degradation, the workflow calls `list_cs_tasks` to assign an immediate review to the account manager. Should the task creation fail, Mastra automatically retries with exponential backoff.

Chain Custom Metric Updates

Tracking complex user behavior requires multiple API calls in sequence. Your agent reads the current tracking definitions using `list_custom_metrics` before deciding what to record. It verifies the exact metric ID required for the specific user action. Once it knows the right ID, the agent executes `post_metric_value` to log the event. If the API rate limits the request, the Mastra AI workflow engine pauses and tries again. You get perfectly accurate usage data without writing custom retry logic.

Require Approval for Account Changes

You probably do not want an autonomous script overwriting enterprise account details. When you configure the MCP server in your Mastra setup, you enable human-in-the-loop validation for destructive actions. When the agent attempts to run `upsert_cs_account` or `upsert_cs_user`, the workflow pauses. A human reviews the proposed CRM changes. Once approved, the agent completes the sync and calls `get_account_health` to verify the update succeeded.

Setup guide

Set up Freshsuccess MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Freshsuccess tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "freshsuccess-mcp-client",
  servers: {
    "freshsuccess-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Freshsuccess Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Freshsuccess tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Freshsuccess transactions"
);
console.log(result.text);

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 Freshsuccess. 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 Freshsuccess 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 Freshsuccess MCP in Mastra AI

Instantiate a new `MCPClient` and map the endpoint URL in the servers object. Call `mcpClient.listTools()` and spread the output into your Agent's tool array.

Yes. If `check_api_status` fails or a metric update times out, the workflow engine catches the error. It applies exponential backoff and attempts the connection again.

Create a workflow that triggers `list_cs_alerts` daily. Use a conditional branch to check the alert type. If it flags a usage drop, route the agent to call `list_cs_tasks` and assign a follow-up.

It does. You flag specific tools like `upsert_cs_account` to require human approval before execution. The workflow suspends until a manager signs off on the CRM update.

Your pending task lists and account metadata travel through an ephemeral Vinkius sandbox. The infrastructure validates the request, executes the tool, and instantly terminates the environment, ensuring your records never rest on our servers.

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