How do I obtain a Feedly Developer Token?

Log in to your Feedly account and navigate to the **Settings > Developer** page to generate a personal access token for prototyping and individual use.

Can I mark articles as read using this agent?

Yes! Use the `mark_as_read` tool with the entry IDs of the articles you wish to clear from your unread stream.

Is it possible to search for new feeds through the agent?

Absolutely. The `search_feeds` tool allows you to search the Feedly global index for specific topics or site URLs to add to your collections.

Feedly MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Feedly
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Feedly through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Feedly "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Feedly?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Feedly MCP Server

Connect your Feedly account to any AI agent and take full control of your news consumption and RSS aggregation through natural conversation.

Pydantic AI validates every Feedly tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Collection Orchestration — List all your curated collections and feeds to organize your information flow natively
Stream Intelligence — Retrieve the latest articles from specific feeds or entire categories with full metadata flawlessly
Read State Management — Mark articles as read or save them for later directly from the cloud without manual UI interaction
Content Discovery — Search for new RSS feeds and trending topics across the entire Feedly index flawlessly
Board & Tag Organization — List and query articles from your personal boards and tagged content natively
User Insights — Access your Feedly profile and subscription metadata through the agent synchronously

The Feedly MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Feedly to Pydantic AI via MCP

Follow these steps to integrate the Feedly MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Feedly with type-safe schemas

Why Use Pydantic AI with the Feedly MCP Server

Pydantic AI provides unique advantages when paired with Feedly through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Feedly integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Feedly connection logic from agent behavior for testable, maintainable code

Feedly + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Feedly MCP Server delivers measurable value.

Type-safe data pipelines: query Feedly with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Feedly tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Feedly and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Feedly responses and write comprehensive agent tests

Feedly MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Feedly to Pydantic AI via MCP:

get_board_contents

Retrieve articles from a specific board

get_entry

Get details for a specific article entry

get_profile

Get current Feedly user profile

get_stream_contents

Retrieve articles for a specific stream (feed, category, or global)

get_subscriptions

List all individual feed subscriptions

get_tag_contents

Retrieve articles associated with a specific tag

list_boards

List all your Feedly boards (saved for later)

list_collections

List all your Feedly collections (categories) and feeds

list_tags

List all your Feedly tags

mark_as_read

Mark specific articles as read

search_feeds

Search for new RSS feeds in the Feedly index

search_topics

Search for trending topics or specific interests

Example Prompts for Feedly in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Feedly immediately.

"List my Feedly collections."

"Show me the latest 5 articles from the 'Tech News' category."

"Search for feeds about 'Edge Computing'."

Troubleshooting Feedly MCP Server with Pydantic AI

Common issues when connecting Feedly to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Feedly + Pydantic AI FAQ

Common questions about integrating Feedly MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Feedly MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.