How to Use the FeedBlitz MCP in AutoGen

Deploy multi-agent AutoGen teams to debate and manage your FeedBlitz marketing campaigns.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FeedBlitz MCP to AutoGen

Create your Vinkius account to connect FeedBlitz to AutoGen 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 FeedBlitz with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate FeedBlitz list hygiene

The `remove_subscriber` tool allows your AutoGen agents to execute list cleanups after debating the risk of churn. One agent can argue for removing an inactive address, while another checks the subscriber's history before executing the tool. This collaborative AutoGen approach prevents accidental unsubscribes on your FeedBlitz lists. By requiring consensus before running the tool, your system maintains list quality without human intervention.

Coordinate FeedBlitz syndications via AutoGen

The `list_syndications` tool gives your AutoGen agent team a clear view of your active FeedBlitz RSS feeds. A coordinator agent can assign specific feeds to sub-agents, who then monitor delivery performance individually. The AutoGen agents can use `get_syndication` to pull detailed settings and discuss optimizations. This multi-agent structure distributes the workload, making it easy to manage dozens of feeds simultaneously.

Run consensus-driven audits with this MCP Server

The `list_metrics` tool feeds raw FeedBlitz campaign performance data into your AutoGen discussion loops. A copywriter agent and an analyst agent can debate why a specific newsletter underperformed based on the returned numbers. Once they reach a consensus, your AutoGen agents can recommend changes or use `add_subscriber` to test a new internal segment. This makes your newsletter optimization process analytical and automated.

Setup guide

Set up FeedBlitz 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 FeedBlitz 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="FeedBlitz_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent FeedBlitz 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="FeedBlitz_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent FeedBlitz 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 FeedBlitz. 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 FeedBlitz 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 FeedBlitz MCP in AutoGen

You use the autogen-ext package and pass the server URL to mcp_server_tools. This automatically converts tools like `add_subscriber` into schemas that your AssistantAgent understands.

Yes, you can pass the same tools list to multiple agents in your group chat. This allows one agent to fetch data using `get_subscriber` while another analyzes it.

The McpToolAdapter handles the schema mapping behind the scenes. It translates the FeedBlitz tool parameters directly into the JSON schemas required by AutoGen's underlying models.

Yes, as long as your local agents can connect to the Vinkius MCP endpoint, they can execute tools like `list_metrics` directly from your local environment.

Yes, all interactions with your FeedBlitz account details and subscriber lists are isolated within our secure V8 sandbox. No data persists on disk, keeping your list metrics safe.

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