How to Use the AgentFire MCP in Mastra AI

Q: How do I initialize the AgentFire MCP Server in Mastra AI?

Instantiate the MCPClient with your server URL. Mastra auto-detects whether to use SSE or Streamable HTTP.

Q: Can Mastra AI retry failed AgentFire lead creations?

Yes. If createlead fails due to network issues, the workflow engine automatically applies exponential backoff and retries the operation.

Q: How do I require human approval for MCP Server updates in Mastra AI?

Enable requireToolApproval on the updatelead tool. The workflow pauses and waits for an admin to confirm the changes.

Q: Does the AgentFire MCP Server support large property queries?

You can use listlistings to fetch bulk data. Mastra handles the memory management for large JSON payloads.

Build resilient property workflows and automate lead routing with Mastra AI and AgentFire.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentFire MCP to Mastra AI

Create your Vinkius account to connect AgentFire 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 AgentFire with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Conditional Lead Workflows

The `create_lead` tool acts as the starting node for your Mastra AI automated sequences. When a new prospect enters the system, you require an email to create the initial record. If the API times out, Mastra's built-in engine catches the failure and applies exponential backoff until the lead registers. Once created, you chain `update_lead` to append preferences based on subsequent interactions. The framework handles the state transitions natively. You just define the logic.

Sync AgentFire MCP Server Data

The `list_contacts` tool pulls your entire address book into the workflow context. You map over this array to cross-reference existing clients with new inquiries. Mastra AI handles the async operations without blocking the main thread. You might also use `get_profile` to pull the assigned agent's details before sending a notification. The entire process runs headless in your cloud environment without manual intervention.

Automate Property Searches

The `search_listings` tool lets your agent query the database based on dynamic parameters. You feed it criteria like price or zip code, and it returns matching properties. If the search yields zero results, you branch the workflow to alert an agent instead. For deep dives on a single home, `get_listing` fetches the granular specs. You pass the resulting JSON down the pipeline to generate marketing copy or draft an email.

Setup guide

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

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

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

Instantiate the `MCPClient` with your server URL. Mastra auto-detects whether to use SSE or Streamable HTTP.

Yes. If `create_lead` fails due to network issues, the workflow engine automatically applies exponential backoff and retries the operation.

Enable `requireToolApproval` on the `update_lead` tool. The workflow pauses and waits for an admin to confirm the changes.

You can use `list_listings` to fetch bulk data. Mastra handles the memory management for large JSON payloads.

Vinkius handles authentication natively and isolates every execution. Your property addresses and client emails never touch persistent storage outside the immediate, ephemeral sandbox for your MCP Server connections.

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