How to Use the Freshcaller MCP in Mastra AI

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

Install @mastra/mcp@latest and initialize MCPClient with your Vinkius server URL. Call mcpClient.listTools() and spread the result into your Mastra Agent configuration.

Q: Can Mastra AI automatically retry failed Freshcaller exports?

Yes. If getexportstatus returns an error or times out, Mastra's workflow engine uses exponential backoff to try again. You configure the retry limits in your workflow definition.

Q: What happens if Mastra AI pulls a bad call recording link?

You build a conditional branch. If getcallrecording returns a broken link, the workflow can fall back to pulling the raw transcript or notify a supervisor via Slack.

Build resilient telecom workflows that handle Freshcaller API limits and call routing failures automatically with 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 Freshcaller MCP to Mastra AI

Create your Vinkius account to connect Freshcaller 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 Freshcaller with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Telecom Provisioning

`list_buyable_numbers` and `list_my_numbers` allow your Mastra AI workflows to automatically search for and verify phone numbers based on traffic demands. You write a workflow that checks if current lines are saturated. If they are, the agent finds available local numbers and queues them for purchase. Mastra handles the inevitable API timeouts. If the search fails, the built-in exponential backoff retries the MCP request before alerting an administrator. You get automated infrastructure scaling without writing custom error handling.

Resilient Data Export Pipelines

`list_export_jobs` and `get_export_status` feed directly into Mastra AI conditional branches to manage massive call center data dumps. The workflow triggers an export, waits, and checks the status. If the job is still pending, the agent loops back and waits longer. You stop relying on manual downloads for monthly reporting. The framework dictates the entire waiting game. Once the status shows as complete, the workflow proceeds to the next step and notifies the data team.

Mastra AI Shift Auditing via MCP Server

`list_calls` and `get_call_details` give your workflow engine the raw material to audit shift performance automatically. A scheduled agent pulls the last hour of phone interactions. It analyzes the wait times and call durations. If a specific interaction exceeds your SLA, the workflow branches. It can automatically flag the ticket or page a manager. The server provides the exact telecom data, while the framework handles the conditional logic.

Setup guide

Set up Freshcaller 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 Freshcaller 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: "freshcaller-mcp-client",
  servers: {
    "freshcaller-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Freshcaller 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 Freshcaller. 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 Freshcaller 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 Freshcaller MCP in Mastra AI

Install `@mastra/mcp@latest` and initialize `MCPClient` with your Vinkius server URL. Call `mcpClient.listTools()` and spread the result into your Mastra Agent configuration.

Yes. If `get_export_status` returns an error or times out, Mastra's workflow engine uses exponential backoff to try again. You configure the retry limits in your workflow definition.

Mastra AI catches the 429 errors from the endpoint automatically. The framework pauses execution and retries the tool call when the limit resets.

You build a conditional branch. If `get_call_recording` returns a broken link, the workflow can fall back to pulling the raw transcript or notify a supervisor via Slack.

The server processes your call logs and export jobs inside an ephemeral, zero-trust environment. The instance authenticates the request, returns the JSON to your Mastra AI client, and terminates immediately, leaving zero traces of your customer phone numbers.

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