How to Use the Close CRM (Inside Sales CRM & Automation API) MCP in LangChain

Q: Can LangChain agents search Close CRM (Inside Sales CRM & Automation API) leads?

Yes, the agent uses the searchdata tool to run advanced filtering queries. It returns paginated results that feed directly into your chain's next step.

Q: Does this MCP Server support updating existing contacts?

Your agent calls updatecontact with the specific fields that need changing. It acts as a PATCH request, leaving the rest of the record untouched.

Build inside sales pipelines where LangChain agents read emails, update opportunities, and send mass outreach in a single run.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Close CRM (Inside Sales CRM & Automation API) MCP to LangChain

Create your Vinkius account to connect Close CRM (Inside Sales CRM & Automation API) 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 CRM (Inside Sales CRM & Automation API) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain Agents via MCP Server

The `search_data` tool lets your agent find specific leads based on custom filters before deciding what action to take next. You build a reasoning loop where the agent checks recent interactions via `list_emails` and `list_calls` to determine if a prospect needs a follow-up. Passing these tools into a LangGraph pipeline gives you exact control over the sequence of events. Output from `create_lead` feeds directly into `create_task`, ensuring your sales reps always have a scheduled touchpoint for every new inbound contact.

Automated Opportunity Management

Your agent uses `create_opportunity` to log new pipeline deals the moment certain conditions are met in your data. It pulls custom field definitions through `get_custom_field_schema` to ensure every required data point gets populated correctly. Tracing these operations in LangSmith shows exactly how many tokens your agent spends analyzing lead data. You can watch the exact inputs and outputs when the agent decides to trigger `update_opportunity` after reading a positive reply.

Bulk Outreach and Activity Tracking

Triggering `bulk_email` allows your agent to initiate mass outreach to a filtered list of leads without leaving the MCP chain. The agent can then monitor the results by polling `list_events` to see who opened, clicked, or replied over the last 30 days. Generating an `activity_report` gives your multi-step pipeline the raw metrics it needs to evaluate campaign performance. The agent parses the response and decides if it needs to adjust the messaging or assign manual follow-ups via `create_task`.

Setup guide

Set up Close CRM (Inside Sales CRM & Automation API) 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 CRM (Inside Sales CRM & Automation API) 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-crm-inside-sales-crm-automation-api-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 CRM (Inside Sales CRM & Automation API) 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 CRM. 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 CRM (Inside Sales CRM & Automation API) 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 CRM (Inside Sales CRM & Automation API) MCP in LangChain

Install langchain-mcp-adapters. Use MultiServerMCPClient pointing to your Vinkius endpoint URL, then call client.get_tools() and pass them to your ReAct agent.

Yes, the agent uses the search_data tool to run advanced filtering queries. It returns paginated results that feed directly into your chain's next step.

Your agent calls update_contact with the specific fields that need changing. It acts as a PATCH request, leaving the rest of the record untouched.

LangSmith automatically traces every MCP tool invocation. You get full visibility into latency, token consumption, and the exact JSON payloads sent to the API.

Vinkius runs inside a V8 Isolate Sandbox with zero-trust architecture. Your leads, emails, and SMS logs never persist after the ephemeral session ends. Auth tokens route directly to the provider.

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