How to Use the Platform.ly MCP in LangChain

Q: How do I connect the Platform.ly MCP Server to LangChain?

Install the langchain-mcp-adapters package and use MultiServerMCPClient to expose Platform.ly tools like createnewcontact directly to your LangChain agent.

Q: Can LangChain agents check existing contacts in Platform.ly?

Yes, your LangChain agent uses searchcontactbyemail to lookup profiles in Platform.ly before running any sequence.

Q: How does LangChain handle errors when updating Platform.ly tags?

If applytagtocontact fails, LangChain catches the exception within the chain, allowing you to view the exact CRM payload inside LangSmith.

Q: Can I run Platform.ly MCP tools alongside other APIs in LangChain?

Absolutely, you can mix Platform.ly tools like getcontactdetails with external databases inside a single LangChain or LangGraph state.

Run multi-step marketing chains in LangChain using direct access to your Platform.ly contacts and pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Platform.ly MCP to LangChain

Create your Vinkius account to connect Platform.ly 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 Platform.ly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-step lead tagging in LangChain

`apply_tag_to_contact` runs automatically inside your LangChain sequential chains whenever a user takes a specific action. Your LangChain agent checks the incoming lead, matches their Platform.ly profile, and applies the right label without you writing manual routing code. If the tag doesn't exist in Platform.ly, the LangChain chain pulls options using `list_project_tags` to make an informed decision on the fly. You get a clear view of this CRM decision-making process directly inside your LangSmith tracing dashboard.

Automated sales pipeline routing with MCP

`create_new_sales_deal` triggers immediately when your LangChain ReAct agent identifies a high-intent conversation in Platform.ly. The LangChain agent evaluates the chat transcript, extracts the budget, and drops the deal straight into your active Platform.ly sales pipeline. To make sure the deal lands in the right spot, the LangChain agent uses `list_sales_pipelines` to find the exact Platform.ly match. This MCP Server keeps your sales team focused on closing rather than copying and pasting data from LangChain chat logs.

Real-time contact updates during chat sessions

`update_existing_contact` allows your LangChain agent to modify Platform.ly customer profiles mid-conversation based on what the user says. If a customer mentions a change in their company size, the LangChain agent corrects the Platform.ly record instantly. Before making any changes in Platform.ly, the LangChain chain runs `search_contact_by_email` to verify the record exists. You don't have to worry about messy Platform.ly data or manual cleanup after a long day of LangChain customer chats.

Setup guide

Set up Platform.ly 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 Platform.ly 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({
    "platformly-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 Platform.ly 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 Platform.ly. 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 Platform.ly 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 Platform.ly MCP in LangChain

Install the `langchain-mcp-adapters` package and use `MultiServerMCPClient` to expose Platform.ly tools like `create_new_contact` directly to your LangChain agent.

Yes, your LangChain agent uses `search_contact_by_email` to lookup profiles in Platform.ly before running any sequence.

If `apply_tag_to_contact` fails, LangChain catches the exception within the chain, allowing you to view the exact CRM payload inside LangSmith.

Absolutely, you can mix Platform.ly tools like `get_contact_details` with external databases inside a single LangChain or LangGraph state.

Your Platform.ly contact emails, sales deals, and project tags are protected within a secure V8 Isolate sandbox. Vinkius handles the MCP connection securely, meaning your raw Platform.ly API keys are never exposed to your LangChain application environment.

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