How to Use the Leadfeeder MCP in Mastra AI

Q: Can Mastra AI retry failed Leadfeeder API calls?

Yes, Mastra handles retries natively. If a call to listaccountvisits fails, the agent will attempt to recover based on the logic you set in your workflow.

Automate your sales workflows with the Leadfeeder MCP Server and 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 Leadfeeder MCP to Mastra AI

Create your Vinkius account to connect Leadfeeder 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 Leadfeeder with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated lead qualification workflows

Build agentic loops that monitor your pipeline without manual intervention. By chaining `list_leads` with `get_lead`, your Mastra agent can identify new visitors and immediately enrich their profiles for your sales team. If a lead meets your criteria, the workflow can branch automatically. You get to define the logic that decides when to alert an SDR versus when to keep monitoring the account.

Conditional visit analysis

Set up triggers based on specific company behaviors. Your agent uses `list_lead_visits` to review recent activity and determines if the account is ready for outreach based on the frequency and depth of their site usage. This removes the guesswork from your sales operations. The agent handles the retries and error checking, so you only see the qualified leads that actually reached your threshold.

Custom feed synchronization

Keep your CRM in sync with your active marketing segments. The agent uses `list_custom_feeds` to find your current filters and `get_custom_feed` to pull the latest company list, ensuring your automated processes always use up-to-date data. This prevents your agents from acting on stale information. You can schedule these checks to run on a loop, keeping your sales pipeline moving while you handle higher-level tasks.

Setup guide

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

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

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

You add the MCP server to your agent configuration. Mastra then automatically exposes tools like `list_leads` and `get_account` to your workflow engine.

Yes, Mastra handles retries natively. If a call to `list_account_visits` fails, the agent will attempt to recover based on the logic you set in your workflow.

It works perfectly. You can write a condition that checks the output of `get_lead` and decides whether to escalate the lead to your CRM or ignore it.

Store your API token in your environment variables. The Mastra MCP client passes it securely to the server, ensuring your organization data remains private.

Absolutely. The server handles raw visitor logs and company firmographics only during the execution of your agent's request. No data is cached or stored by the transport layer.

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