How to Use the Feedly MCP in AutoGen

Q: How do I register Feedly MCP Server tools with AutoGen agents?

Install autogen-extmcp and use mcpservertools to fetch the tool definitions. You can then pass this tool list directly to your AssistantAgent constructor.

Q: Can AutoGen agents collaborate to organize my Feedly boards?

Yes. One agent can list your current boards using listboards, while another fetches content using getboardcontents to decide if an article should be archived.

Q: Does AutoGen support the write operations like marking Feedly entries as read?

Yes. Agents can invoke markasread once they have processed an article. This helps keep your actual Feedly inbox clean and synchronized.

Let AutoGen agents debate and curate your Feedly news streams automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Feedly MCP to AutoGen

Create your Vinkius account to connect Feedly 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 Feedly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent curation via the Feedly MCP Server

AutoGen lets you build a team of specialized agents to process your news. This Feedly MCP Server allows one agent to fetch new articles using `get_stream_contents`, while a second agent filters them for relevance. Instead of a single model making decisions, your agents debate which articles deserve your attention. They use `list_collections` to categorize the selected feeds into clean buckets.

Automated triage and tagging with AutoGen

Keep your feeds organized without lifting a finger. This Feedly MCP Server enables AutoGen agents to analyze incoming articles and use `get_tag_contents` to check existing categories. The agents can negotiate whether to label an article under a specific tag. Once they reach a consensus, they run `mark_as_read` on the noise so you only see high-value updates.

Collaborative topic discovery and research

Researching a new market requires looking beyond your current feeds. This Feedly MCP Server lets AutoGen agents coordinate to run `search_topics` and find trending angles on complex subjects. A research agent can pull details with `get_entry`, while a critical agent challenges the source's credibility. They collaborate to build a curated list of sources for your boards.

Setup guide

Set up Feedly 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 Feedly 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="Feedly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use `mcp_server_tools` to fetch the tool definitions. You can then pass this tool list directly to your `AssistantAgent` constructor.

Yes. One agent can list your current boards using `list_boards`, while another fetches content using `get_board_contents` to decide if an article should be archived.

You define the system prompts and conversation flow. If one agent wants to flag an article from `get_stream_contents` and another disagrees, they debate until they meet your consensus rules.

Yes. Agents can invoke `mark_as_read` once they have processed an article. This helps keep your actual Feedly inbox clean and synchronized.

Your developer token is injected securely into the Vinkius V8 sandbox. The article data debated by your AutoGen agents is kept strictly within your session memory.

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