How to Use the Marchex MCP in LangChain

Q: How do I connect the Marchex MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. Initialize the MultiServerMCPClient with your HTTP transport URL and pass the resulting tools to your createagent function.

Q: Can LangChain agents search specific Marchex calls?

Yes. Your agent can call the searchcalls tool with specific parameters like date ranges or caller IDs. It then parses the JSON response to feed the next step in your analytical chain.

Q: Does this setup support multiple account hierarchies?

It handles account structures natively. Your agent can run listaccounts to get the parent IDs, then pass those into getaccountdetails to pull specific billing or configuration data.

Build intelligent call tracking pipelines. Connect the Marchex MCP Server directly to your LangChain agents for automated marketing analysis.

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 LangChain

Create your Vinkius account to connect Marchex to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Marchex data in LangChain

Your ReAct agents need raw telecom data to make accurate decisions. Connecting this MCP Server gives your LangChain pipelines direct access to Marchex call intelligence. The agent decides exactly when to pull campaign metrics and how to parse the resulting JSON payload. You build the chain, and the tools handle the execution. An agent can fire off `list_campaigns` to find active marketing pushes, then immediately pipe those IDs into `get_call_analytics` to aggregate performance data. LangSmith tracks every token and API call along the way so you know exactly what happened.

Deep dive into call performance

Marketing teams waste hours manually matching phone calls to ad spend. You can automate that entire workflow. Pass a specific date range to `search_calls` and let your agent filter the results based on duration or call outcome. When a specific call looks anomalous, the chain digs deeper automatically. It invokes `get_call_details` to pull the exact metadata for that interaction. You get the raw facts fed directly into your pipeline without ever logging into a dashboard.

Map your tracking infrastructure

Managing hundreds of phone numbers across different client accounts gets messy fast. Your automated reporting script can map the whole hierarchy in seconds. It starts with `list_accounts` to grab the top-level structure of your organization. From there, the agent loops through the accounts to pull the underlying assets. It runs `list_numbers` and `get_number_details` to verify which tracking lines belong to which campaigns. You always know exactly where your inbound traffic originates.

Setup guide

Set up Marchex MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Marchex tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "marchex-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Marchex transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and `langgraph`. Initialize the `MultiServerMCPClient` with your HTTP transport URL and pass the resulting tools to your `create_agent` function.

Yes. Your agent can call the `search_calls` tool with specific parameters like date ranges or caller IDs. It then parses the JSON response to feed the next step in your analytical chain.

It handles account structures natively. Your agent can run `list_accounts` to get the parent IDs, then pass those into `get_account_details` to pull specific billing or configuration data.

LangSmith automatically traces every tool invocation. You can see exactly what inputs the agent sent to `get_campaign_details` and measure the latency of the response.

The MCP architecture keeps your data isolated. When your agent requests call durations and caller metadata via `get_call_analytics`, the server processes the request within a zero-trust V8 sandbox. The connection remains ephemeral and drops immediately after the payload transfers.

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