How to Use the Instantly MCP in LangChain

Q: How do I Instantly trace API calls made by LangChain in LangSmith?

Every time your agent calls listleads or addleads, LangSmith logs the exact payload and latency. You see the exact inputs and outputs of the MCP tools in your execution trace.

Q: Can I manage multiple sender accounts at once?

Yes, the listaccounts tool gives you a complete list of your connected inboxes. You can run loops to check getaccountstats across your entire setup.

Feed live Instantly cold email metrics into your LangChain runs to pause failing campaigns before they trash your sender score.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Instantly MCP to LangChain

Create your Vinkius account to connect Instantly 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 Instantly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Instantly analytics to LangChain guardrails

Stop letting dead campaigns burn your domain reputation. When your LangChain agent pulls data with `get_campaign_analytics`, it immediately checks if your bounce rate crossed the danger zone. If it did, the chain triggers `pause_campaign` without waiting for a human to log in and look at a dashboard. This isn't just about saving your domains; it's about automated recovery. The same LangChain sequence can pull the bad list via `list_leads`, trace the source of the bounces in LangSmith, and queue up a cleaner batch of prospects.

Build recursive lead injection loops in LangChain

Cold outreach lives and dies by lead flow. You can configure a LangChain agent to monitor your CRM, filter for new matches, and use `add_leads` to inject them directly into active campaigns. This MCP Server gives your chain the exact endpoint it needs to keep your pipeline full. Because LangChain handles multi-step reasoning, the agent doesn't just blindly dump names. It calls `list_campaigns` first to find the highest-performing sequence, checks the current load with `get_account_stats`, and only drops leads where they will actually get sent.

Multi-account balancing with this MCP Server

Managing dozens of sender profiles is a nightmare. This MCP Server lets your LangChain runner call `list_accounts` to inspect every single connected inbox. You get raw, unvarnished performance data sent straight into your execution chain. If one of your sender accounts starts lagging, the agent shifts the traffic. It queries `list_subsequences` to see where the bottleneck is, then reroutes the next batch of leads to healthier profiles.

Setup guide

Set up Instantly 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 Instantly 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({
    "instantly-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 Instantly 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 Instantly. 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 Instantly 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 Instantly MCP in LangChain

Use the MultiServerMCPClient to fetch the tools, then pass them to your agent. When the agent calls `get_campaign`, the JSON payload flows directly into your next chain step.

Yes, you build a decision node in your chain. The agent checks `get_campaign_analytics`, and if the bounce rate is over three percent, it immediately triggers `pause_campaign` to protect your domain.

Every time your agent calls `list_leads` or `add_leads`, LangSmith logs the exact payload and latency. You see the exact inputs and outputs of the MCP tools in your execution trace.

Yes, the `list_accounts` tool gives you a complete list of your connected inboxes. You can run loops to check `get_account_stats` across your entire setup.

Your API keys and lead email addresses never touch third-party servers. All requests to query `list_leads` or update sending accounts run inside a secure, ephemeral V8 isolate sandbox that wipes itself clean after every execution.

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