How to Use the CallFire MCP in Mastra AI

Q: How do I initialize CallFire tools inside Mastra AI?

Install the @mastra/mcp package and instantiate a new MCPClient using your Vinkius server URL. Call listTools() to pull the telephony operations. Then spread those functions directly into your Agent's tool array.

Build resilient MCP Server communication workflows and auto-retry failed texts 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 CallFire MCP to Mastra AI

Create your Vinkius account to connect CallFire 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 CallFire with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Conditional Messaging Pipelines

The `send_sms` tool dispatches text alerts exactly when your workflow rules dictate. Mastra AI evaluates the surrounding logic, such as a failed credit card charge, and triggers the message. If the carrier network drops the request, the framework's built-in exponential backoff automatically tries again. Running `get_account_info` verifies available funds before firing off a massive broadcast. Mastra handles that conditional branching natively. This ensures your agent never initiates a campaign it cannot afford.

Automate Voice Call Fallbacks with Mastra AI

The `send_voice_call` tool initiates an automated phone call when an urgent situation escalates. Your workflow engine monitors the outcome and decides the next step based on the result. If a critical alert goes to voicemail, the agent instantly pivots and sends a text message fallback. Running `get_call_details` returns the duration, cost, and hangup cause for a specific interaction. The framework uses that hard data to route the user down different paths. You can program the agent to schedule a follow-up or close the ticket based on the actual call length.

Audit Webhooks and Rented Keywords

The `list_keywords` tool exposes every short code and text string you currently lease for incoming traffic. Mastra AI can periodically audit this list against your active marketing campaigns. If a keyword is sitting idle, the agent flags it for a human manager to review and cancel. Executing `list_webhooks` pulls the current routing table for all inbound replies. You can require tool approval before the agent modifies these endpoints. This keeps a strict human-in-the-loop safety net over your production infrastructure.

Setup guide

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

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

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

Install the `@mastra/mcp` package and instantiate a new `MCPClient` using your Vinkius server URL. Call `listTools()` to pull the telephony operations. Then spread those functions directly into your Agent's tool array.

The framework handles retries natively through its workflow engine. If a dial hits a temporary carrier error, the system waits and tries again based on your configured backoff settings. You do not have to write custom loop logic.

Yes, you can gate any destructive or expensive action. Setting `requireToolApproval` on operations like sending broadcasts forces the agent to pause. A human operator must manually authorize the action before it leaves your system.

The framework automatically detects the correct connection method. We recommend using Streamable HTTP for Vinkius endpoints. This avoids long-lived SSE connection drops during extended workflow executions.

We enforce a strict zero-trust architecture across all telephony operations. When your agent pulls data or reads a message body, that information passes through a temporary, isolated execution environment. The sandbox vanishes the millisecond the HTTP response 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