How to Use the Agency Elephant MCP in LangChain

Q: How do I use LangChain to add a new lead to a drip campaign in Agency Elephant?

You build a chain where the first step calls createlead. The second step takes the leadid from that output and passes it to the triggerdripcampaign tool along with the campaignid.

Q: Can a single LangChain agent create a lead and then get its details in Agency Elephant?

Yes. That's a classic two-step chain. The agent calls createlead, gets the new leadid, and then immediately calls getleaddetails with that ID to confirm the record was created correctly.

Build LangChain agents that manage your insurance leads, from creation to campaign enrollment, in a single, traceable chain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agency Elephant MCP to LangChain

Create your Vinkius account to connect Agency Elephant 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 Agency Elephant with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Lead Operations Together

This MCP server gives your agent tools to manage the entire lead lifecycle. You can build a chain that starts by creating a new prospect with `create_lead`, and in the very next step, uses the new lead's ID to enroll them in a welcome sequence with `trigger_drip_campaign`. In LangChain, this is what composability is all about. The output from one tool call becomes the input for the next. This lets you construct dependable, multi-step workflows for your agency. And since every call is logged in LangSmith, you get a full trace of what your agent did, what data it used, and why.

Build Custom Agency Reports with LangChain

Give your agent a simple goal, like 'summarize our active campaigns'. The agent can then use the `list_campaigns` tool to get the raw data. From there, it might decide to use `list_leads` to count enrollments for each one. This isn't a pre-canned report. Your LangChain agent decides the sequence of tool calls needed to answer your question. It can cross-reference information from `list_lead_groups` and `get_lead_details` to build a picture of what's happening in your agency right now. It's a reasoning process, not just a script.

Automate Prospect Assignment

Your agent can monitor for new leads and assign them to the right person. A simple chain can periodically call `list_leads` to check for unassigned prospects. Once it finds one, it can pull your team roster with `list_workspace_users` to see who's available. This is how you build an administrative assistant with LangChain. You provide the Agency Elephant tools, and the agent uses them to connect the dots. The entire process is a repeatable chain you can run on a schedule, making sure no new lead ever falls through the cracks.

Setup guide

Set up Agency Elephant 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 Agency Elephant 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({
    "agency-elephant-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 Agency Elephant 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 Agency Elephant. 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 Agency Elephant 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 Agency Elephant MCP in LangChain

You build a chain where the first step calls `create_lead`. The second step takes the `lead_id` from that output and passes it to the `trigger_drip_campaign` tool along with the `campaign_id`.

Yes. That's a classic two-step chain. The agent calls `create_lead`, gets the new `lead_id`, and then immediately calls `get_lead_details` with that ID to confirm the record was created correctly.

After installing the MCP adapter, you instantiate the client and call `client.get_tools()`. You then pass that list of tools directly into the `create_agent` function when you build your agent.

It just works. Because the tools are standard LangChain tools, every call your agent makes—like `list_leads` or `get_lead_details`—is automatically captured in your LangSmith traces. You'll see the inputs, outputs, and latency for each step.

Your agent will handle lead data, including names and contact details, as well as campaign information and workspace user lists. All connections go through Vinkius, where your server runs in a temporary, isolated sandbox for each session. The data is only used for the transaction and then destroyed.

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