How to Use the HeyReach MCP in LangChain

Q: Can LangChain automatically pause a HeyReach campaign when a lead replies?

Yes, you can set up a chain that checks listconversations for new replies. If a reply is found, the LangChain agent calls pausecampaign using the campaign ID to stop further automated follow-ups.

Build multi-step LinkedIn prospecting chains using LangChain and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HeyReach MCP to LangChain

Create your Vinkius account to connect HeyReach 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 HeyReach with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Outreach Chains

The HeyReach MCP Server lets you link your LinkedIn outreach directly into LangChain's sequential chain runnables. Your LangChain agent can run `list_campaigns` to find active targets, fetch a lead's history with `list_lead_campaigns`, and then decide whether to push new prospects into the queue using `add_leads_to_campaign`. Because every step is tracked, you can monitor the exact latency and token usage of these LinkedIn operations inside LangSmith. This keeps your automated LangChain prospecting from running wild, so you don't hit LinkedIn's rate limits.

Smart Inbox Management via LangGraph

This MCP Server enables stateful inbox agents to read and respond to LinkedIn messages within your LangGraph workflows. The LangChain agent calls `list_conversations` to pull recent chats, analyzes the sentiment, and uses `send_linkedin_message` to fire off a contextual reply without you opening a browser. LangChain handles the session state, meaning your agent remembers previous interactions. It can verify who is sending the message by calling `list_linkedin_accounts` to keep your multi-account LangChain workspace organized.

Programmatic Campaign Control via MCP Server

Stop campaigns instantly when a lead responds by hooking up the HeyReach MCP Server to your LangChain chains. The LangChain agent checks if a lead replied, then uses `pause_campaign` to halt the automated sequence and prevent embarrassing double-messages. Once your sales rep reviews the thread, the chain triggers `resume_campaign` to keep things moving. It's smart to run `get_api_profile` first to make sure your connection hasn't dropped.

Setup guide

Set up HeyReach 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 HeyReach 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({
    "heyreach-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 HeyReach 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 HeyReach. 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 HeyReach 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 HeyReach MCP in LangChain

Use the LangChain MCP adapter to register the server tools. Your agent can then use `add_leads_to_campaign` to push new leads directly from your database into an active LinkedIn sequence.

Yes, you can set up a chain that checks `list_conversations` for new replies. If a reply is found, the LangChain agent calls `pause_campaign` using the campaign ID to stop further automated follow-ups.

You should implement rate-limiting runnables or custom delays in your LangChain sequence. This prevents tools like `send_linkedin_message` from triggering too fast and triggering LinkedIn's spam detection.

No, the server handles workspace-level authentication. Your agent calls `list_linkedin_accounts` to see all connected senders and routes actions to the correct profile automatically.

Vinkius runs the server in an ephemeral sandbox, meaning your API keys and lead profiles are never stored persistently on our end. All requests to fetch lead details are proxied directly to the endpoint and wiped as soon as the session ends.

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