How to Use the Substack MCP in LangChain

Q: What specific data types does the MCP Server touch regarding privacy?

The server touches subscriber data via listsubscribers, which contains audience records. It also handles content metadata when calling getpost or listposts.

Build complex workflows and multi-step reasoning chains with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Substack MCP to LangChain

Create your Vinkius account to connect Substack 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 Substack with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Substack Data Aggregation with LangChain MCP Server

You don't just get data; you build a sequence. Your agent can first call `get_post_stats` to see which posts perform best, then use the post IDs found to execute `list_posts`. This creates an observable chain of reasoning that dictates your next move.

Multi-step Substack Audience Analysis for LangChain

Want to track growth? Use a multi-server chain: first, pull the overall publication info via `get_publication_info`. Next, feed that context into an agent that calls `list_subscribers` and then summarizes those findings. The output of one step directly informs the next, making your pipelines highly deterministic.

Profiling Content Performance Using LangChain

Run a full content audit by chaining tools together. Start with `list_posts` to get recent content titles, pass those titles into an agent that calls `get_post`, and finally gather detailed metrics using `get_post_stats`. This process models real-world editorial review cycles.

Setup guide

Set up Substack 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 Substack 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({
    "substack-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 Substack 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 Substack. 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 Substack 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 Substack MCP in LangChain

LangChain uses the MCP Server to model complex workflows. Instead of simple reports, you build chains that gather data—like running `get_post_stats` and then feeding those metrics into a separate analysis step.

The ideal scenario involves analyzing content performance. You can build an agent that first checks `list_posts`, determines which ones need promotion, and then pulls the stats to justify a marketing action.

Yes. Your agent can execute a chain starting by getting general publication info (`get_publication_info`) and immediately follow up by calling `list_subscribers`. This allows you to monitor audience size fluctuations across multiple steps.

Absolutely. Because LangChain is designed for multi-server aggregation, it handles complex data flows well. You can combine this Substack server with other API calls to build truly massive reasoning pipelines.

The server touches subscriber data via `list_subscribers`, which contains audience records. It also handles content metadata when calling `get_post` or `list_posts`.

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