How to Use the Feedly MCP in Pydantic AI

Q: How do I configure the Feedly MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset class pointing to your Vinkius endpoint. Pass the toolset instance directly into your Agent constructor to register the tools.

Q: How does Pydantic AI handle the listsubscriptions tool output?

The output of listsubscriptions is parsed into a validated Python list of subscription objects. Your agent can inspect the verified attributes like feed ID and title with full autocomplete support in your IDE.

Build type-safe ingestion pipelines with Pydantic AI and Feedly to catch schema drift before it breaks your agents.

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 Pydantic AI

Create your Vinkius account to connect Feedly to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe stream parsing in Pydantic AI

The `get_stream_contents` tool delivers structured article data that Pydantic AI validates against strict type definitions at runtime. If the Feedly API structure changes or returns unexpected null fields, your agent catches the validation error instantly. This prevents silent data corruption in your downstream databases. By running this MCP Server, your Python code remains stable because every feed title, URL, and publish date is guaranteed to match your expected schema.

Validated subscription workflows

The `subscribe_to_feed` tool allows your agent to safely add new RSS feeds to your account. Pydantic AI validates the input parameters before the request ever leaves your server, preventing malformed URLs from hitting the API. Once subscribed, the agent can use `get_feed_metadata` to check that the feed is active. The returned metadata is parsed into a clean Pydantic model, making it easy to write type-safe logic around feed updates.

Clean feed state management

The `mark_articles_as_read` tool lets your agent manage your inbox state without risking accidental bulk deletions. Because Pydantic AI enforces strict typing on article IDs, you never have to worry about passing malformed identifiers to the API. You can combine this with `list_categories` to build automated inbox-zero scripts that run safely on any LLM. If the model attempts to pass an invalid category format, the system rejects it immediately at the boundary.

Setup guide

Set up Feedly MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "feedly-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Feedly tools.",
)

result = await agent.run("List recent Feedly transactions")
print(result.output)

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 Pydantic AI

Install pydantic-ai-slim[mcp] and use the unified MCPToolset class pointing to your Vinkius endpoint. Pass the toolset instance directly into your Agent constructor to register the tools.

The framework will raise a validation error immediately. This ensures your agent fails loudly and safely rather than proceeding with corrupted or hallucinated article details.

Yes. Pydantic AI is model-agnostic, meaning you can connect the Feedly tools to local models via Ollama or run them against commercial APIs like Anthropic and OpenAI.

The output of list_subscriptions is parsed into a validated Python list of subscription objects. Your agent can inspect the verified attributes like feed ID and title with full autocomplete support in your IDE.

Yes. The integration runs on Vinkius's zero-trust infrastructure, which handles your developer token securely. Pydantic AI only sees the validated JSON responses returned by the MCP tools, never your raw API keys or credentials.

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