How to Use the CUFinder MCP in LangChain

Q: How do I add CUFinder tools to a LangChain agent?

You install langchain-mcp-adapters and use the MultiServerMCPClient to connect to the Vinkius endpoint. From there, call client.gettools() to import the B2B lookup tools directly into your agent constructor.

Q: Can I monitor CUFinder API latency inside LangChain?

Yes, because every call to enrichlinkedin or getcompanyinfo runs as a native tool, LangSmith captures the exact execution time. You can see the payload size and response speed for every single lookup.

Q: What happens if a domain search fails during an MCP run?

The finddomain tool returns an empty result, which your LangChain agent catches. You can write a fallback path in your chain to search by company name instead of failing the entire execution.

Feed verified B2B data directly into your LangChain chains to automate prospecting and track tool execution in real-time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CUFinder MCP to LangChain

Create your Vinkius account to connect CUFinder 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 CUFinder with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain CUFinder Domain and Email Lookups in LangChain

The `find_domain` and `find_email` tools allow your LangChain agent to resolve a company's web address and grab lead emails in a single run. You configure a sequential chain where the output of the domain search instantly feeds the email finder without manual intervention. LangSmith tracks every step of this MCP tool sequence, mapping out exactly how much latency each API call adds to your pipeline. This level of observability lets you debug failing lookups instantly and optimize how your chain handles missing B2B contacts.

Validate Lead Quality with an MCP Server Verification Step

The `verify_email` tool checks email validity on the fly before your LangChain agent passes data to downstream CRM integrations. This step blocks bad emails from polluting your database by making validation a strict requirement in your agentic workflow. You can branch your LangGraph state based on the verification result, routing valid leads to your sales sequence and flagged addresses to a manual review queue. This keeps your pipeline moving without relying on dirty data.

Deepen Account Intelligence via LangChain Multi-Tool Chains

The `get_company_tech` and `get_company_revenue` tools pull financial metrics and software stack details directly into your LLM prompt context. Your agent uses this data to customize outreach templates based on the prospect's actual budget and current technology. Combining these data points inside a LangChain reasoning loop lets your model build highly targeted sales pitches dynamically. It means your outbound team gets rich company profiles without leaving their terminal or agent workspace.

Setup guide

Set up CUFinder 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 CUFinder 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({
    "cufinder-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 CUFinder 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 CUFinder. 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 CUFinder 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 CUFinder MCP in LangChain

You install `langchain-mcp-adapters` and use the `MultiServerMCPClient` to connect to the Vinkius endpoint. From there, call `client.get_tools()` to import the B2B lookup tools directly into your agent constructor.

Yes, because every call to `enrich_linkedin` or `get_company_info` runs as a native tool, LangSmith captures the exact execution time. You can see the payload size and response speed for every single lookup.

Yes, the Vinkius client is stateless by default, but you can call `client.session()` to maintain context across multiple steps in your chain. This helps when passing account info from `find_employees` down to email validation.

The `find_domain` tool returns an empty result, which your LangChain agent catches. You can write a fallback path in your chain to search by company name instead of failing the entire execution.

All emails, phone numbers, and employee profiles fetched via the tools run inside isolated, ephemeral V8 sandboxes. Vinkius never logs or caches your target prospect data, ensuring your sales intelligence remains strictly private.

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