How to Use the Salespanel MCP in LangChain

Q: How do I connect the Salespanel MCP Server to my LangChain agent?

You'll use the MultiServerMCPClient from the LangChain MCP adapter. Just pass it your Vinkius endpoint URL. Then, call client.gettools() and pass the resulting list to your agent factory.

Q: What's the best way to handle multiple leads with Salespanel and LangChain?

The best approach is to use a map-reduce chain. First, use listanonymousvisitors or listcontacts to get a list. Then, have a separate chain process each lead individually with getcontactdetails and listengagementevents to build a complete profile.

Build autonomous sales intelligence pipelines in LangChain. Connect your agent to Salespanel and let it find and qualify leads for you.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salespanel MCP to LangChain

Create your Vinkius account to connect Salespanel to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Salespanel with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find Leads Before They Raise Their Hand

This tool lets your agent watch your website for you. It starts with `list_anonymous_visitors` to see who's showing up. Then, it digs deeper, using `get_visitor` and `get_company` to piece together a profile from just a few clicks. The real trick is chaining these calls. Your LangChain agent can build a sequence: find a visitor, enrich their data, check them against `list_contacts`, and decide if they're a new lead or an existing customer. It's a full-funnel scout that never sleeps.

Build Custom Lead Scoring with this MCP Server

Stop relying on static lead scores. With this MCP server, your agent can score leads based on what they're doing right now. It pulls a real-time event stream using `list_activity_feeds` and `list_engagement_events`. Your LangChain agent can assign points for specific actions—viewing the pricing page, downloading a whitepaper—and then use `get_contact_details` to get the full picture. If a lead's score crosses a threshold, the agent can flag it for immediate follow-up. You define the logic; the agent executes it.

Segment Contacts on the Fly

Your agent gets direct access to Salespanel's segmentation engine. It can pull your existing segments with `list_lead_segments` or check the details of a specific one using `get_segment`. This isn't just about reading data. Your agent can create its own temporary segments in your code. For example, find all contacts from `list_accounts` in the finance industry who visited the site this week. That's a segment you can act on instantly, without waiting for marketing ops.

Setup guide

Set up Salespanel 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 Salespanel 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({
    "salespanel-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 Salespanel 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 Salespanel. 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 Salespanel 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 Salespanel MCP in LangChain

You'll use the `MultiServerMCPClient` from the LangChain MCP adapter. Just pass it your Vinkius endpoint URL. Then, call `client.get_tools()` and pass the resulting list to your agent factory.

No, this specific server provides read-only access. It's designed for intelligence gathering—using tools like `list_contacts` and `get_company` to inform your agent's decisions, not to modify the source data in Salespanel.

The best approach is to use a map-reduce chain. First, use `list_anonymous_visitors` or `list_contacts` to get a list. Then, have a separate chain process each lead individually with `get_contact_details` and `list_engagement_events` to build a complete profile.

Yes, that's the point. You can create a chain where the agent first gets company info from `get_company`, then uses that info to search a different database or trigger another API call. The tools from this MCP server become just one part of a larger workflow.

This server only processes Salespanel identifiers, contact details, and visitor engagement data. Vinkius isolates each request in a sandbox, and your MCP server token is the only key needed. The server itself is ephemeral and doesn't store your info.

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