How to Use the Feedly MCP in Vercel AI SDK

Q: How do I fetch my Feedly boards in Vercel AI SDK?

You call listboards using the MCP client provided by the SDK. It returns an array of your saved boards that you can map directly to your UI state.

Q: Can Vercel AI SDK filter my Feedly streams automatically?

Yes. You pass the results from getstreamcontents into your model's system prompt to filter out irrelevant entries. The agent then decides which ones to present.

Stream real-time Feedly data directly into your Vercel AI SDK interface without the usual loading lag.

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 Vercel AI SDK

Create your Vinkius account to connect Feedly to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time feed ingestion for Vercel AI SDK

Feed your UI live content by calling `get_stream_contents` directly through your edge functions. This MCP Server pipes article data straight into your streamText calls. Your users see headlines pop up as the agent finds them. No more stale data or waiting for backend jobs to finish before the component renders.

Automate article triage

Use `mark_as_read` to clear your queue once the agent processes an entry. You can trigger this after your model summarizes the text. It keeps your dashboard clean while the AI client handles the heavy lifting of sorting through your daily noise.

Search and discover new sources

Expose `search_feeds` to your users so they can find new RSS sources via natural language. The agent maps their intent to the Feedly index. This gives your app a native feel where the search bar actually does the work of finding and adding content to their collections.

Setup guide

Set up Feedly MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Feedly tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Feedly transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You call `list_boards` using the MCP client provided by the SDK. It returns an array of your saved boards that you can map directly to your UI state.

Yes. You pass the results from `get_stream_contents` into your model's system prompt to filter out irrelevant entries. The agent then decides which ones to present.

Not if you use the standard MCP transport. You connect the server, expose the tools, and the client handles the data flow.

You provide your developer token through the environment variables during server initialization. The MCP server handles the handshake for every request.

Your reading history stays within the ephemeral sandbox of the server. We only touch the specific article metadata you request through the tool calls.

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