Bring Rss Aggregator
to Pydantic AI
Learn how to connect Feedly to Pydantic AI and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Feedly MCP Server?
Connect your Feedly account to any AI agent and take full control of your news aggregation and content curation workflows through natural conversation.
What you can do
- Feed Orchestration — List and manage your subscribed news sources programmatically, including adding or removing RSS/Atom feeds
- Stream Intelligence — Retrieve the latest entries (articles) from specific feeds or categories and monitor unread counts in real-time
- Content Extraction — Programmatically fetch complete article text and metadata to perform deep analysis and summaries via your agent
- Organization Control — Manage your Feedly categories and personal tags to maintain a structured and high-fidelity reading environment
- Reading Workflow — Mark articles as read and manage your reading list programmatically to streamline your news consumption
How it works
1. Subscribe to this server
2. Retrieve your Developer Access Token from Feedly (Settings > Integrations > Developer Token)
3. Start managing your news curation from Claude, Cursor, or any MCP client
No more manual scrolling through endless articles. Your AI acts as your dedicated news analyst and content curator.
Who is this for?
- Market Researchers — instantly track industry news and retrieve full article contents for deep analysis using natural language
- Content Strategists — monitor trending topics across specific feeds and manage curation tags without leaving your workspace
- Busy Professionals — automate the process of marking articles as read and summarizing daily highlights through simple AI queries
Built-in capabilities (10)
Get full content of an article
Get metadata for a specific feed
Retrieve articles from a stream
Get your Feedly profile
List your Feedly categories
List all subscribed feeds
List your personal tags
Mark one or more articles as read
Follow a new news source
Stop following a news source
Why Pydantic AI?
Pydantic AI validates every Feedly tool response against typed schemas, catching data inconsistencies at build time. Connect 10 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.
- —
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 in Pydantic AI
Feedly and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Feedly to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Feedly in Pydantic AI
The Feedly 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. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Feedly for Pydantic AI
Every tool call from Pydantic AI to the Feedly MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I get a Feedly Developer Token?
Log in to Feedly, go to your account settings, navigate to Integrations, and select 'Developer Token' to request your access key.
Can the agent mark articles as read automatically?
Yes! Use the mark_articles_as_read tool and provide an array of article IDs to clear them from your unread list programmatically.
How many articles can I retrieve at once?
The get_stream_contents tool allows you to specify a count (default 20, max 1000) for retrieving articles from a stream.
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.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai