How to Use the Marchex MCP in AutoGen

Q: How do I load Marchex MCP Server tools into an AutoGen agent?

Install autogen-extmcp. Use mcpservertools with a StreamableHttpServerParams configuration, then pass the resulting tool list to your AssistantAgent. The adapter handles schema conversion automatically.

Q: How do agents handle large lists of phone calls?

They break the problem down. An agent will use searchcalls with strict date filters to grab manageable chunks of data, then pass those records to a summarization agent for processing.

Q: Will AutoGen agents automatically fix broken Marchex campaigns?

No. The current toolset is read-only. Your agents can use getcampaigndetails to diagnose a configuration issue and debate the cause, but a human must implement the fix in the dashboard.

Build multi-agent systems that debate marketing performance. Connect the Marchex MCP Server to AutoGen to analyze call data.

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 AutoGen

Create your Vinkius account to connect Marchex to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Marchex data with AutoGen

Single-agent systems miss the nuance in complex marketing data. By connecting this MCP Server, you give your AutoGen teams direct access to raw telecom metrics. A data-gathering agent pulls the numbers while an analytical agent challenges the interpretation. The framework handles the debate automatically. One agent fires `get_call_analytics` to report a spike in volume, but a secondary quality-assurance agent runs `search_calls` to prove those calls were mostly spam. They negotiate the final insight before presenting it to you.

Audit campaign performance

You need different perspectives to evaluate ad spend properly. You can assign one agent to represent cost and another to represent conversion. The cost agent uses `list_campaigns` to find active spending across the platform. The conversion agent takes those campaign IDs and runs `get_campaign_details` to check the actual configuration. If the numbers look off, the agents debate whether the tracking setup is broken or the campaign is just failing. You get a consensus, not a blind guess.

Verify account infrastructure

Managing telecom assets requires strict oversight. You can build a security agent dedicated entirely to auditing your setup. It runs `list_accounts` and `list_users` to map who has access to what systems. A separate compliance agent cross-references that data. It calls `list_numbers` and `get_number_details` to ensure every tracking line routes to an approved destination. If they find a discrepancy, they flag it in the conversation log for human review.

Setup guide

Set up Marchex MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Marchex tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Marchex_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Marchex data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Marchex_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Marchex data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with a `StreamableHttpServerParams` configuration, then pass the resulting tool list to your `AssistantAgent`. The adapter handles schema conversion automatically.

Yes. You can equip a dedicated data-retrieval agent with the MCP Server tools, while other agents in the chat rely on that specific agent to fetch call records and campaign stats.

They break the problem down. An agent will use `search_calls` with strict date filters to grab manageable chunks of data, then pass those records to a summarization agent for processing.

No. The current toolset is read-only. Your agents can use `get_campaign_details` to diagnose a configuration issue and debate the cause, but a human must implement the fix in the dashboard.

Your data never persists on the host machine. When agents request caller IDs and timestamps via `get_call_details`, the MCP server executes the query in an ephemeral V8 isolate. The payload exists only long enough for the agents to reach a consensus before the memory wipes.

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