How to Use the Heymarket MCP in LangChain

Q: How do I connect Heymarket to a LangChain agent?

Install the langchain-mcp-adapters package. You initialize a MultiServerMCPClient with your Heymarket endpoint and pass the resulting tools directly to your agent constructor.

Q: Can LangChain read my Heymarket message history?

Your agent calls getchathistory to pull past conversation context. This prevents the bot from asking questions the customer already answered yesterday.

Q: Does Heymarket support MMS through LangChain?

You can send multimedia messages. The sendsmsmessage tool handles both SMS and MMS, provided you pass the correct parameters and media URLs.

Build LangChain agents that text customers, update contact records, and manage your shared inbox natively.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Heymarket MCP to LangChain

Create your Vinkius account to connect Heymarket 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 Heymarket with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain SMS workflows in LangChain

The Heymarket MCP Server lets your ReAct agents handle customer texts from start to finish. A single prompt triggers a chain that reads incoming messages via `list_active_chats` and extracts the caller's phone number. Your agent then queries internal databases for order status before firing off a reply with `send_sms_message`. Every step is traceable in LangSmith, so you know exactly why the agent sent a specific text.

Automate CRM updates with this MCP Server

Keeping contact records accurate usually requires manual data entry. Now, your LangGraph pipelines pull new numbers directly from `get_chat_history` and register them automatically. The agent executes `create_contact` the moment an unknown number texts your business. If a customer texts from a new address, the pipeline runs `update_contact_profile` to keep your system of record perfectly synced.

Route messages across your team

Shared inboxes get messy when nobody claims a thread. You can build a routing agent that monitors `list_active_chats` and evaluates the sentiment of incoming texts. Based on the content, the agent uses `list_team_members` to find an available rep and assigns the conversation using `update_chat_status`. The customer gets a faster reply, and your sales team stops stepping on each other's toes.

Setup guide

Set up Heymarket 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 Heymarket 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({
    "heymarket-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 Heymarket 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 Heymarket. 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 Heymarket 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 Heymarket MCP in LangChain

Install the `langchain-mcp-adapters` package. You initialize a MultiServerMCPClient with your Heymarket endpoint and pass the resulting tools directly to your agent constructor.

Your agent calls `get_chat_history` to pull past conversation context. This prevents the bot from asking questions the customer already answered yesterday.

You can send multimedia messages. The `send_sms_message` tool handles both SMS and MMS, provided you pass the correct parameters and media URLs.

LangSmith automatically traces every tool invocation. It shows you the exact latency and token consumption for operations like `list_contacts`.

Vinkius runs this MCP Server in an ephemeral V8 Isolate Sandbox. Phone numbers, contact names, and raw SMS payloads from `get_message_details` never persist on the middleware. The connection relies on a single endpoint token, enforcing zero-trust access to your workspace.

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