How to Use the Marchex MCP in OpenAI Agents SDK

Q: How do I initialize the Marchex MCP Server inside the OpenAI Agents SDK?

Install the package and configure MCPServerStreamableHttp with your Vinkius endpoint. Pass the server instance directly to the Agent constructor in the mcpservers list to let it auto-discover tools.

Q: What happens if a call search returns zero results?

The searchcalls tool returns an empty list. Your Python agent will receive this response and can decide whether to broaden the search parameters or stop execution.

Deploy production OpenAI Agents SDK workflows that pull real-time call tracking and campaign metrics directly from your Marchex account.

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 OpenAI Agents SDK

Create your Vinkius account to connect Marchex to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Call Auditing with OpenAI Agents SDK

The Marchex MCP Server provides `search_calls` and `get_call_details` to feed raw conversation data directly into your agent's execution pipeline. Your Python agent uses these tools to inspect call records, check duration, and flag unusual customer interactions without manual intervention. Because the SDK enforces strict runtime validation, your agent won't act on bad data. The built-in guardrails check the phone numbers and call paths returned by `get_number_details` before passing them to specialized downstream agents.

Track Campaign Performance with MCP Server

Running `list_campaigns` and `get_campaign_details` lets your OpenAI Agents SDK setup monitor active marketing channels on the fly. The agent fetches performance metrics, identifies low-performing numbers, and formats updates for your executive reports. You get full execution tracing on the OpenAI dashboard for every tool call. If an agent tries to pull analytics via `get_call_analytics`, you can trace the exact parameters passed to the API to prevent unauthorized account access.

Manage Accounts via MCP Server

This MCP Server exposes `list_accounts` and `list_users` so your specialized agents can coordinate across multi-tenant setups. One agent can check client access levels while another pulls operational data, handing off tasks as needed. Setup requires passing the server parameters to `MCPServerStreamableHttpParams` and setting `cacheToolsList=True` for speed. This ensures your agents resolve account hierarchies instantly without hitting rate limits on repeated schema lookups.

Setup guide

Set up Marchex MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Marchex tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Marchex tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Marchex tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Marchex Agent",
            instructions="You have access to Marchex tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package and configure `MCPServerStreamableHttp` with your Vinkius endpoint. Pass the server instance directly to the Agent constructor in the `mcp_servers` list to let it auto-discover tools.

Yes, you can control tool exposure at the client level during initialization. This prevents your agent from calling administrative tools like `list_users` while still letting it run analytical queries.

The SDK handles streamable HTTP connections efficiently, but you should configure retry logic on your agent's execution loop. Setting `cacheToolsList=True` reduces overhead by caching the tool definitions.

The `search_calls` tool returns an empty list. Your Python agent will receive this response and can decide whether to broaden the search parameters or stop execution.

All call records, tracking numbers, and campaign metrics are processed in isolated V8 sandboxes. Your Vinkius endpoint token secures the connection, ensuring that raw voice analytics data is never stored or exposed to external networks.

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