How to Use the Close MCP in LangChain

Q: Can LangChain agents create new records in Close?

Yes. The agent uses the createlead tool when it determines a new prospect fits your criteria. You control the logic that triggers the creation.

Build multi-step sales reasoning pipelines by connecting the Close MCP Server to your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Close MCP to LangChain

Create your Vinkius account to connect Close 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 Close with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Close tools in LangChain

The Close MCP Server gives your LangChain agents direct read and write access to your inside sales CRM. You build chains that pull a batch of records using `list_leads` and then feed those IDs downstream. The ReAct agent decides which lead needs attention based on the intermediate results. Tracing via LangSmith shows exactly how long the API took to respond. When the agent triggers `create_lead`, you see the exact token usage and payload sent. Connect this to a vector store in the same chain to enrich the lead data before insertion.

Automate daily CRM workflows

Your sales automation pipeline starts by pulling the current context. The agent runs `get_current_user` to verify permissions, then executes `list_crm_tasks` to see what needs doing today. It parses the task list and decides what action to take next. Because LangChain handles state across the chain, you pass the output of the task list directly into a notification node. Your agent reviews the tasks and alerts the right rep, all without a human opening the CRM interface.

Inspect sales opportunities

Complex deal reviews require deep context. The agent fires `list_opportunities` to grab the open pipeline, then iterates through the results. For any high-value deal, it automatically triggers `get_lead_details` to pull the full communication history. The framework's composability shines here. Instead of writing custom API wrappers, your agent just calls the MCP tools in sequence. You get a fully observable pipeline that summarizes the health of your sales floor.

Setup guide

Set up Close 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 Close 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({
    "close-alternative-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 Close 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 Close. 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 Close 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 Close MCP in LangChain

Install the langchain-mcp-adapters package via pip. Then pass the Vinkius endpoint token to MultiServerMCPClient and call get_tools() to arm your agent.

Yes. The agent uses the create_lead tool when it determines a new prospect fits your criteria. You control the logic that triggers the creation.

The server provides a standardized tool schema that ReAct agents understand natively. You skip writing custom parsers and get instant LangSmith observability for every request.

It works perfectly. The agent reads the tool descriptions and decides when to pull list_opportunities versus when to dig into a specific lead.

Your deal amounts and prospect contact information stay protected. Vinkius runs the connection inside an ephemeral V8 isolate sandbox that spins down immediately after the agent finishes the task.

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