How to Use the Feedly MCP in AutoGen

Q: How do AutoGen agents access my Feedly streams?

You register the getstreamcontents tool with your AutoGen AssistantAgent using the McpToolAdapter. This lets any agent in your group conversation query your feeds when needed.

Q: Can AutoGen agents subscribe to new Feedly feeds?

Yes. Agents can use the subscribetofeed tool to follow new RSS sources after debating and agreeing that a source is relevant to your research goals.

Q: How do I pass Feedly MCP tool schemas to AutoGen?

The McpToolAdapter automatically translates the Feedly server's schemas into the format AutoGen's conversational agents expect, handling all parameter mapping behind the scenes.

Q: Can an AutoGen critic agent verify Feedly source metadata?

Yes. The critic agent can call getfeedmetadata to check a source's details, helping the group decide if the feed is trustworthy before pulling articles.

Deploy AutoGen agents that debate, filter, and curate your Feedly subscriptions through multi-agent consensus.

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 debate over Feedly MCP Server streams

By exposing `get_stream_contents`, this server lets your AutoGen agents run collaborative debates over your feeds. Don't let a single agent decide what's important. You can set up a research agent to fetch articles and a critic agent to evaluate their relevance. This consensus-driven approach filters out the noise. The critic agent can check feed details with `get_feed_metadata` to verify source authority, ensuring only high-quality information makes it to your attention.

Collaborative feed management via AutoGen

This server exposes `get_user_profile` and `list_categories` to let your AutoGen agents manage your reading list through collaborative discussion. One agent can analyze your current reading habits, while another suggests new sources. This MCP Server allows your team to analyze what's missing. If a feed doesn't meet the group's quality standards, a consensus is reached to remove it. The execution agent then calls `unsubscribe_from_feed` to keep your Feedly account clean and focused.

Coordinate complex tag and read workflows

By exposing `list_tags` and `mark_articles_as_read`, this server allows your AutoGen agents to split up heavy curation tasks. While one agent scans your streams, another manages organization by applying labels. They coordinate their actions through structured agent conversations. Once the team agrees an article has been processed, a dedicated archiver agent calls `mark_articles_as_read`. This prevents other agents from wasting tokens on the same content in future runs.

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

You register the `get_stream_contents` tool with your AutoGen `AssistantAgent` using the `McpToolAdapter`. This lets any agent in your group conversation query your feeds when needed.

Yes. Agents can use the `subscribe_to_feed` tool to follow new RSS sources after debating and agreeing that a source is relevant to your research goals.

The `McpToolAdapter` automatically translates the Feedly server's schemas into the format AutoGen's conversational agents expect, handling all parameter mapping behind the scenes.

Yes. The critic agent can call `get_feed_metadata` to check a source's details, helping the group decide if the feed is trustworthy before pulling articles.

Your Feedly developer token is stored securely in Vinkius's zero-trust environment and is never exposed to the LLM or the AutoGen agents during runtime.

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