How to Use the Marchex MCP in Mastra AI

Q: How do I add Marchex tools to my Mastra AI agent?

Instantiate the client and call mcpClient.listTools(). Spread that array directly into your agent's tool configuration.

Q: How do I handle Marchex tool approvals in Mastra AI?

Use the requireToolApproval flag on sensitive operations like account modifications. The workflow halts until a human signs off.

Orchestrate resilient call tracking workflows with Mastra AI and the Marchex integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marchex MCP to Mastra AI

Create your Vinkius account to connect Marchex 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 Marchex with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Marchex MCP Server workflow routing

Telecom data gets messy. You need a system that can handle edge cases when querying `search_calls` and `get_call_details`. Mastra's workflow engine lets you build conditional branches based on what those endpoints return. If a specific call record is missing, the agent doesn't just crash. It can pivot, search for a different tracking number, or alert an administrator.

Automated Campaign Retries

Hitting rate limits is a reality when you pull massive datasets. Firing off `list_campaigns` followed by dozens of `get_call_analytics` requests will eventually stall. This framework catches those failures automatically. Exponential backoff kicks in, pausing the execution and retrying the request until the telecom platform responds.

Safe Number Provisioning

Buying and assigning phone numbers costs money. You might want the AI to suggest inventory using `list_numbers`, but you probably don't want it acting autonomously just yet. Setting up human-in-the-loop approvals is straightforward. The agent pauses after finding the right number, waits for an admin to click approve, and only then continues the sequence.

Setup guide

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

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

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

Instantiate the client and call `mcpClient.listTools()`. Spread that array directly into your agent's tool configuration.

Yes. The framework includes built-in exponential backoff. It will automatically re-attempt failed calls to the MCP Server.

Use the `requireToolApproval` flag on sensitive operations like account modifications. The workflow halts until a human signs off.

The client auto-detects the transport layer. It connects to the Vinkius endpoint using either Server-Sent Events or Streamable HTTP without manual configuration.

The integration connects via a zero-trust architecture. Campaign IDs and performance data pass through an isolated sandbox that wipes all memory the second the workflow 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