How to Use the Substack MCP in AutoGen

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

The server touches subscriber records via listsubscribers and basic content metadata through getpost. These are used as evidence in agent debates.

Drive consensus-based decisions using AutoGen.

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 AutoGen

Create your Vinkius account to connect Substack to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debating Content Strategy with AutoGen MCP Server

Setup multiple agents: one 'Marketing' agent that calls `get_leaderboard`, and another 'Editorial' agent that uses `list_posts`. They debate which content should be promoted, using the live data outputs as evidence in their discussion.

Consensus-Driven Subscriber Growth Analysis for AutoGen

You can simulate a strategy meeting. One agent pulls current stats with `get_post_stats`, while another reviews total subscribers via `list_subscribers`. They debate the most effective growth channel, resulting in a clear consensus action plan.

Simulating Publication Health Checks using AutoGen

Have agents negotiate the platform's status. One agent checks `get_publication_info` for overall health, and another reviews recent posts via `list_posts`. They argue about necessary maintenance tasks or content gaps.

Setup guide

Set up Substack MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Substack tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Substack_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Substack data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Substack_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Substack data")
    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 AutoGen

AutoGen doesn't just report; it makes agents debate the reports. For instance, if one agent calls `get_post_stats`, another can challenge that data point and force a more thorough investigation.

The ideal scenario involves conflict resolution. You set up agents to debate conflicting goals—e.g., maximize revenue vs. maintain community openness—using real `get_publication_info` data as evidence.

Yes. You can have agents role-play different stakeholders (e.g., a reader, an author, and a marketer) using `get_post` data to generate varied viewpoints on the same piece of work.

It does. By passing tool outputs into the conversational framework, you force deliberation between competing perspectives until a final decision is reached, which is AutoGen's specialty.

The server touches subscriber records via `list_subscribers` and basic content metadata through `get_post`. These are used as evidence in agent debates.

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