How to Use the Feedly MCP in Pydantic AI

Q: How do I initialize the Feedly toolset in Pydantic AI?

Use the unified MCPToolset constructor with your Vinkius HTTP endpoint. Pass this toolset directly into your Agent setup using the toolsets argument.

Q: Can I use Pydantic AI to validate Feedly board schemas?

Yes, when calling listboards, the returned list of boards is validated against internal models, ensuring your agent always has accurate IDs before calling getboardcontents.

Build bulletproof news curation pipelines with Pydantic AI, enforcing strict type safety on every Feedly feed and article import via our managed MCP Server.

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 curation using Pydantic AI and MCP

Do not let malformed RSS feeds crash your production pipelines. By connecting this MCP Server to your Pydantic AI agent, every article returned by `get_entry` is validated against strict Python schemas before your model even sees it. If a feed source returns corrupted metadata, the system catches it at the boundary. This keeps your ingestion pipeline from breaking when external feeds change. Your agents can parse complex feeds using `get_stream_contents` knowing that every title, author, and timestamp matches the exact types your application expects.

Validate board structure and collections instantly

Keeping your taxonomy organized is a pain. When your agent calls `list_collections` or `list_boards`, Pydantic AI validates the structure of your categories and saved lists at runtime. This prevents your agent from hallucinating non-existent tags or writing to the wrong boards. If you need to organize your reading lists, the agent can safely pull current configurations using `list_tags`. The validated data can then be used to route articles to the correct internal databases without risking type mismatches.

Error-free feed discovery and subscription updates

Searching for new sources shouldn't clutter your database. When your agent runs `search_feeds` or `search_topics`, the results are cleanly structured into typed Python objects. This allows you to programmatically filter out low-quality sources before adding them to your subscriptions. Once validated, you can safely trigger write operations like `mark_as_read` to keep your feeds clean. The entire loop runs with strict validation, ensuring your feed state remains perfectly synchronized.

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-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

Use the unified `MCPToolset` constructor with your Vinkius HTTP endpoint. Pass this toolset directly into your `Agent` setup using the `toolsets` argument.

The framework will raise a validation error at runtime. This prevents your agent from processing incomplete articles from `get_stream_contents` or corrupting your downstream databases.

Yes, when calling `list_boards`, the returned list of boards is validated against internal models, ensuring your agent always has accurate IDs before calling `get_board_contents`.

Yes, you can connect your agent to this server using either Streamable HTTP or SSE transports, depending on your network architecture.

We run every connection inside a secure, short-lived sandbox. No article content from `get_entry` or profile details from `get_profile` ever touch persistent storage, keeping your credentials completely locked down.

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