How to Use the Kit (ConvertKit) MCP in LangChain

Q: How do I connect Kit (ConvertKit) to my LangChain agent?

Install langchain-mcp-adapters. Use MultiServerMCPClient to connect to the endpoint, call client.gettools(), and pass them directly to your ReAct agent setup.

Q: Can LangChain automatically fix bad Kit (ConvertKit) tool calls?

Yes. If the agent calls searchsubscriberbyid with an email instead of a numeric ID, the API returns an error. The ReAct loop catches that error, corrects the input, and tries again.

Q: How do I handle persistent context across sessions?

LangChain agents are stateless by default. Use client.session() to keep context alive so the agent remembers which forms it just pulled.

Build multi-step subscriber workflows by wiring Kit (ConvertKit) into your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kit (ConvertKit) MCP to LangChain

Create your Vinkius account to connect Kit (ConvertKit) 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 Kit (ConvertKit) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Wire the Kit MCP Server into ReAct agents

The Kit (ConvertKit) MCP Server gives your LangChain agent direct access to email marketing endpoints. You pass the tools into your agent executor, and it decides when to fire off `list_subscribers` or grab macro metrics via `get_account_growth_summary`. You get full observability through LangSmith. Every API request the agent makes shows up in your trace logs. If a chain fails because it hallucinated a tag ID, you see exactly what it sent to `apply_tag_to_subscriber` and fix the prompt immediately.

Chain opt-ins and segmentation

This server exposes `add_subscriber_to_form` and `apply_tag_to_subscriber` so your pipeline handles acquisition and tagging in one pass. An agent reads an incoming lead from a database, drops them into a specific form, and immediately tags them based on their industry. You don't have to write custom integration code. The agent pulls available tags using `list_all_tags` and matches them against the user profile. If a tag is missing, the chain stops and alerts you.

Run automated subscriber audits

Your agent uses `get_subscriber_details` and `update_subscriber` to clean up stale lists automatically. You can build a chron job in LangGraph that checks subscriber engagement scores and updates their custom fields. When you need a broader view, the agent calls `list_email_sequences` to map out where users currently sit in your funnels. It feeds that raw data into your LLM to summarize campaign health.

Setup guide

Set up Kit (ConvertKit) 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 Kit (ConvertKit) 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({
    "kit-convertkit-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 Kit (ConvertKit) 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 Kit. 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 Kit (ConvertKit) 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 Kit (ConvertKit) MCP in LangChain

Install `langchain-mcp-adapters`. Use `MultiServerMCPClient` to connect to the endpoint, call `client.get_tools()`, and pass them directly to your ReAct agent setup.

Yes. If the agent calls `search_subscriber_by_id` with an email instead of a numeric ID, the API returns an error. The ReAct loop catches that error, corrects the input, and tries again.

It works out of the box. You map the tools to specific nodes in your graph. One node handles pulling forms while another processes the logic to route subscribers.

LangChain agents are stateless by default. Use `client.session()` to keep context alive so the agent remembers which forms it just pulled.

The server processes raw email addresses and numeric IDs. Vinkius runs the connection in an ephemeral V8 Isolate Sandbox that shuts down immediately after the LangChain tool call finishes. No subscriber records touch disk.

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