How to Use the Cloze MCP in LangChain

Q: How do I trace Cloze tool calls inside LangChain?

Use LangSmith to trace calls made by getperson or createproject. You will see the exact payload sent to the Cloze API, the execution latency, and the token count for each CRM action.

Q: Can a LangChain agent create a project and a person in one run?

Yes. Your LangChain agent uses ReAct reasoning to call createperson first, captures the new contact details, and then immediately invokes createproject to link them to a new deal.

Q: How do custom Cloze fields map to LangChain tool schemas?

The listcustomfields tool exposes your specific CRM configuration directly to the LangChain agent. This allows the model to dynamically adjust its input schema before calling updateperson.

Q: What happens if a contact already exists during a LangChain run?

The updateperson tool uses the email address as a unique match key. Your LangChain agent handles this by checking if the email exists via getperson before attempting a new write.

Build multi-step LangChain reasoning loops that update contacts and manage deals inside your Cloze CRM using 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 Cloze MCP to LangChain

Create your Vinkius account to connect Cloze 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 Cloze with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chaining Contact Updates in LangChain

The `get_person` tool fetches raw contact profiles from Cloze directly into your LangChain run context using this MCP tool. Your agent inspects the returned email, checks for missing details, and instantly triggers `update_person` to fill in the blanks. This execution sequence runs inside a single LangSmith-monitored chain. You see exactly how the contact payload moves from the retrieval step to the update tool without writing glue code.

Automate Deals via the Cloze MCP Server and LangChain

The `create_project` tool lets your LangChain ReAct agent spin up new deals or properties in Cloze based on incoming email text. The agent parses the raw text, extracts the budget, and maps it to the right schema fields. If the agent needs custom fields, it calls `list_custom_fields` first to ensure the deal payload matches your specific CRM setup. This prevents API schema errors before the agent attempts to write the new project.

Tag-Based Pipeline Routing

The `search_people_by_tag` tool retrieves targeted lists of leads from Cloze to feed directly into your LangChain sequential chains. Your agent pulls every contact with a specific tag and passes them one by one to downstream email templates. You control the flow by combining this search tool with standard LangChain vector store lookups to personalize outreach based on both CRM tags and semantic history.

Setup guide

Set up Cloze 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 Cloze 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({
    "cloze-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 Cloze 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 Cloze. 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 Cloze 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 Cloze MCP in LangChain

Use LangSmith to trace calls made by `get_person` or `create_project`. You will see the exact payload sent to the Cloze API, the execution latency, and the token count for each CRM action.

Yes. Your LangChain agent uses ReAct reasoning to call `create_person` first, captures the new contact details, and then immediately invokes `create_project` to link them to a new deal.

The `list_custom_fields` tool exposes your specific CRM configuration directly to the LangChain agent. This allows the model to dynamically adjust its input schema before calling `update_person`.

The `update_person` tool uses the email address as a unique match key. Your LangChain agent handles this by checking if the email exists via `get_person` before attempting a new write.

Your contact emails, names, and deal details pass through Vinkius's secure sandbox directly to your LangChain runtime. We run this MCP server in a zero-trust sandbox, ensuring your customer data never leaks to external logs.

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