How to Use the LeadsRx MCP in LangChain

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

Install langchain-mcp-adapters and use the MultiServerMCPClient to point to your Vinkius endpoint. This registers all ten attribution tools so your agent can call them during execution.

Q: How does LangSmith help debug LeadsRx tool calls in a LangChain pipeline?

Every time your LangChain agent calls getconversiondetails, LangSmith logs the exact payload and response latency. You see the precise data exchanged, making it easy to spot API errors or bad parameters.

Q: What is the best way to handle multiple marketing channels in an MCP pipeline?

Use listchannels to get the active channels, then loop through them using getcampaignresults for each ID. This lets your agent build a structured comparison table directly in the chain's state.

Feed multi-touch attribution data directly into your LangChain reasoning loops to adjust ad spend based on real-time conversions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LeadsRx MCP to LangChain

Create your Vinkius account to connect LeadsRx 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 LeadsRx with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace campaign performance in LangChain

The `get_campaign_results` tool pulls raw attribution metrics directly into your agent's active memory. Your LangChain agent evaluates these numbers, compares performance across channels, and decides which campaign needs immediate budget adjustments. Instead of guessing which ads drive revenue, your pipeline checks the actual return on investment. LangSmith tracks every step of this analysis, showing you exactly how the agent processed the attribution data before making its decision.

Map customer touchpoints across active chains

The `list_touchpoints` tool exposes the exact path customers take before they buy. Your agent chains this tool with `get_touchpoint_details` to isolate specific ad interactions that triggered the purchase behavior. By feeding these touchpoints into a ReAct loop, the MCP agent identifies channels that deserve more credit. You get a clear picture of the buyer journey without manually stitching together disparate marketing reports.

Feed real-time conversions into your agent

The `add_conversion` tool pushes new conversion events directly to LeadsRx from your LangChain execution path. This keeps your attribution models updated as soon as a user action occurs on your platform. Your LLM chain uses `list_conversions` to verify these events against existing records before making budget recommendations. This MCP Server setup ensures your marketing decisions rely on fresh, validated conversion data.

Setup guide

Set up LeadsRx 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 LeadsRx 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({
    "leadsrx-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 LeadsRx 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 LeadsRx. 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 LeadsRx 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 LeadsRx MCP in LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` to point to your Vinkius endpoint. This registers all ten attribution tools so your agent can call them during execution.

Yes, the agent uses the tool schemas to determine when to call `get_campaign_results` or `list_channels` based on your prompt. It evaluates the raw JSON output to decide the next analytical step in its chain.

Every time your LangChain agent calls `get_conversion_details`, LangSmith logs the exact payload and response latency. You see the precise data exchanged, making it easy to spot API errors or bad parameters.

Use `list_channels` to get the active channels, then loop through them using `get_campaign_results` for each ID. This lets your agent build a structured comparison table directly in the chain's state.

Absolutely. Your LeadsRx conversion logs and touchpoint details remain inside Vinkius's secure, ephemeral V8 isolate sandbox. No data persists on the host, and all API calls require a single, encrypted endpoint token.

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