How to Use the Feedly MCP in Google ADK

Q: Can my Google ADK agent write Feedly stream data directly to BigQuery?

Yes. Your agent can use getstreamcontents to fetch the latest articles, format them as JSON, and then use your Google Cloud tools to load that data into a BigQuery table.

Feed millions of tokens of Feedly stream data into your Google ADK pipelines for long-context Gemini reasoning.

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 Google ADK

Create your Vinkius account to connect Feedly to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context feed analysis in Google ADK

The `get_stream_contents` tool pulls raw text from your curated feeds directly into your Gemini agent's million-token context window. This allows your Google ADK agent to analyze weeks of industry updates in a single pass without running out of memory. Since Gemini excels at processing massive chunks of data, you can feed entire streams into the model. The agent uses `get_article_details` to pull full text for deep analysis, then writes the distilled insights straight to BigQuery.

Enterprise feed curation using Google ADK

The `subscribe_to_feed` tool lets your Gemini-powered agent dynamically update your company's intelligence sources based on database triggers. If a new competitor emerges in your BigQuery dataset, the agent automatically follows their official blog. You can restrict which tools are exposed to the agent using the tool_names filter in the Google ADK setup. For instance, you might expose `list_subscriptions` and `get_feed_metadata` while blocking the unsubscribe tool to prevent accidental data loss.

Tag-based filtering for Vertex AI models

The `list_tags` tool allows your agent to find articles that you have manually flagged as high-priority. This bridges the gap between your manual curation in Feedly and your automated machine learning pipelines on Vertex AI. By using `mark_articles_as_read` through the MCP Server, your agent can clear out noise automatically after processing. This keeps your main feed clean so you only see what actually requires human eyes.

Setup guide

Set up Feedly MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Feedly tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Feedly_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Feedly tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the google-adk package and use the McpToolset class with your Vinkius HTTP URL. Pass this toolset directly into your LlmAgent instance to make all ten tools available to Gemini.

Yes. Your agent can use get_stream_contents to fetch the latest articles, format them as JSON, and then use your Google Cloud tools to load that data into a BigQuery table.

Yes. While Vinkius hosts the Feedly integration as a hosted HTTP endpoint, Google ADK can connect to it using the streamable HTTP protocol, giving your cloud-deployed agents direct access to MCP tools.

Gemini's massive context window easily processes the full-text HTML and plain text payloads returned by get_article_details without needing aggressive truncation or complex chunking strategies.

Your Feedly profile and stream data are fetched on demand via secure API calls. Vinkius runs the MCP Server in an ephemeral sandbox, ensuring your authentication tokens are never stored in your Google Cloud environment or logged in Vertex AI.

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