How to Use the Icypeas MCP in LangChain

Q: How does LangChain track the credit usage of Icypeas tools?

You can use LangSmith tracing to monitor every call to getcredits and trace the exact inputs and outputs of your email searches. This gives you a clear audit trail of your API spend per run.

Q: Do I need a persistent session to list my outreach campaigns?

No, tools like listcampaigns are stateless by default. Your agent can query campaign details instantly, though you can use LangGraph state to pass campaign IDs between steps.

Q: How does this setup secure my prospect lists and email data?

All email addresses and lists processed via verifyemail go through an ephemeral V8 sandbox that wipes data immediately after execution. Your API key is stored strictly on your local environment, meaning your raw prospect data never sits exposed on third-party servers.

Connect your LangChain agents directly to Icypeas to find and verify lead emails in multi-step reasoning chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Icypeas MCP to LangChain

Create your Vinkius account to connect Icypeas 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 Icypeas with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain verification steps with LangChain

`verify_email` lets your LangChain agents check deliverability on the fly before dumping contacts into your CRM. By feeding the output of your lead searches straight into this verification tool, you build self-correcting pipelines that stop bad data at the door. You can track this entire data flow inside LangSmith to see exactly how your agent handles catch-all domains. It shows you the raw latency and credit costs for every single check without any guesswork.

Build autonomous prospecting loops via this MCP Server

`search_prospects` acts as the starting point for autonomous lead generation chains running on your LangChain setup via this MCP Server. Your agent can run searches based on custom filters and then immediately pass those raw profiles to the next node in your graph. This setup removes the manual export-import step entirely from your daily sales stack. Since LangChain handles state across multi-step runs, your agent remembers which lists it already checked during the session.

Monitor credit burn dynamically

`get_credits` gives your LangChain loops real-time visibility into your remaining API balance before executing high-volume runs. You can program your chain to pause or alert your team if your balance drops below your safety threshold. This guardrail prevents runaway agent loops from eating your entire monthly budget on a single bad recursive search. It keeps your automated outreach budget highly predictable.

Setup guide

Set up Icypeas 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 Icypeas 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({
    "icypeas-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 Icypeas 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 Icypeas. 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 Icypeas 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 Icypeas MCP in LangChain

You should configure your LangChain run with standard exponential backoff retry logic. Since the server passes raw HTTP status codes from the API, your agent can catch 429 codes and pause execution to protect your limits.

Yes, you can register this MCP server alongside your database tools in your agent initialization. Your agent can pull company names from your database, pass them to find_email, and save the verified address back to your database in one run.

You can use LangSmith tracing to monitor every call to get_credits and trace the exact inputs and outputs of your email searches. This gives you a clear audit trail of your API spend per run.

No, tools like list_campaigns are stateless by default. Your agent can query campaign details instantly, though you can use LangGraph state to pass campaign IDs between steps.

All email addresses and lists processed via verify_email go through an ephemeral V8 sandbox that wipes data immediately after execution. Your API key is stored strictly on your local environment, meaning your raw prospect data never sits exposed on third-party servers.

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