How to Use the Feedly MCP in Google ADK

Q: Can I restrict which Feedly tools my Google ADK agent can access?

Yes, you can use the toolnames filter in your Python setup. This allows you to limit the agent to read-only tools like getboardcontents while blocking write actions.

Q: How does Google ADK handle large payloads from Feedly streams?

The framework passes the JSON output from getstreamcontents straight to Gemini. Thanks to the massive context window, the model can analyze hundreds of articles without hitting size limits.

Q: Can I combine Feedly data from Google ADK with BigQuery datasets?

Easily. Your agent can fetch articles using getentry and immediately write structured summaries or sentiment scores into your BigQuery tables for long-term storage.

Q: What transport method should I use for this MCP connection on Google Cloud?

We recommend HTTP transport using StreamableHttpServerParameters for cloud deployments. It provides a stable, serverless connection compared to local stdio pipes.

Feed Gemini's million-token context window with deep industry data by linking this Feedly MCP Server to your Google ADK pipelines.

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

Feed massive context windows using this MCP Server

Gemini models excel at processing massive volumes of text at once. This protocol setup allows your Google ADK agent to pull entire industry feeds using `get_stream_contents` and digest hundreds of articles in a single run. You don't have to worry about running out of context space when analyzing complex market trends. The agent can cross-reference raw articles against your enterprise datasets in BigQuery. By combining `get_entry` with your internal tables, you build a powerful intelligence pipeline that connects external news with internal metrics.

Curate enterprise intelligence with target filters

Keep your Vertex AI models focused on high-signal content. You can use the `tool_names` parameter in your `McpToolset` setup to restrict your Google ADK agent's access to highly specific tools like `get_board_contents` or `get_tag_contents`. This prevents the agent from wasting cycles browsing random feeds. Your agents can read curated boards that your analysts have already vetted. This ensures that your automated reporting systems only process verified, high-value information.

Discover new market trends on Google Cloud

Expand your monitoring footprint automatically. Your Google ADK agents can use `search_topics` to find emerging trends, then immediately run `search_feeds` over the active MCP link to locate the best RSS feeds covering those topics. This allows your enterprise agents to discover and suggest new sources without human intervention. Once a new feed is identified, the agent can list existing structures using `list_collections` to recommend exactly where the new source should be categorized. It keeps your corporate knowledge base fresh and organized.

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

Yes, you can use the `tool_names` filter in your Python setup. This allows you to limit the agent to read-only tools like `get_board_contents` while blocking write actions.

The framework passes the JSON output from `get_stream_contents` straight to Gemini. Thanks to the massive context window, the model can analyze hundreds of articles without hitting size limits.

Easily. Your agent can fetch articles using `get_entry` and immediately write structured summaries or sentiment scores into your BigQuery tables for long-term storage.

We recommend HTTP transport using `StreamableHttpServerParameters` for cloud deployments. It provides a stable, serverless connection compared to local stdio pipes.

Vinkius routes all API requests through an isolated, zero-trust container. Your Feedly developer token and subscription lists are decrypted only in memory during active tool execution and never logged.

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