How to Use the Miniflux (RSS Reader) MCP in Vercel AI SDK

Q: How do I connect Miniflux (RSS Reader) to Vercel AI SDK?

Install @ai-sdk/mcp and instantiate the MCP client with the HTTP transport pointing to your Vinkius endpoint. Pass the tools directly to streamText to let your agent manage feeds.

Q: How does Miniflux (RSS Reader) handle UI updates in Vercel AI SDK?

The agent calls database-mutating tools like updateentriesstatus and yields the raw result. Your frontend streams this state change, updating the UI elements immediately.

Q: Do I need to manage feed caching manually?

No, the server handles feed updates via refreshfeed and internal database operations. Your agent asks for the data, and the server serves cached or newly fetched entries depending on your query parameters.

Render your RSS feed updates directly in your React UI using Vercel AI SDK to build live feed readers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Miniflux (RSS Reader) MCP to Vercel AI SDK

Create your Vinkius account to connect Miniflux (RSS Reader) 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 Miniflux (RSS Reader) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live UI Feed Discovery

Your application uses `discover_subscriptions` and `create_feed` to find and add RSS sources instantly. The AI client handles the discovery loop in the background, displaying found feeds to the user as they are parsed from any raw URL. When a user drops a URL into your Next.js input, the edge-compatible client resolves the feed and inserts it into the database. You don't write custom API endpoints to handle RSS parsing; the server takes care of the extraction and returns clean JSON schemas for your frontend.

Real-time Article Triage in Vercel AI SDK

This MCP Server exposes `list_entries` and `update_entries_status` to let your UI instantly update read states without page refreshes. The streaming architecture sends entry lists directly to your UI components, allowing users to batch-mark articles as read or unread. Your React components receive the state changes live. Processing hundreds of articles happens in the background, updating the database state while the user watches the feed clean itself up in real-time.

Direct Content Extraction

The `fetch_entry_content` tool retrieves the full, parsed text of any article directly into your client context. This bypasses typical paywalls and heavy ad layouts, serving raw, readable content to your custom reader component. Your frontend renders the clean HTML or Markdown instantly. Because this runs on edge-compatible transport, users get immediate access to original article bodies without waiting for slow server-side rendering cycles.

Setup guide

Set up Miniflux (RSS Reader) 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 Miniflux (RSS Reader) 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 Miniflux (RSS Reader) 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 Miniflux. 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 Miniflux (RSS Reader) 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 Miniflux (RSS Reader) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and instantiate the MCP client with the HTTP transport pointing to your Vinkius endpoint. Pass the tools directly to `streamText` to let your agent manage feeds.

Yes, the MCP client is fully compatible with Vercel edge runtime environments. It communicates via standard HTTP POST requests, avoiding Node-specific dependencies.

The agent calls database-mutating tools like `update_entries_status` and yields the raw result. Your frontend streams this state change, updating the UI elements immediately.

No, the server handles feed updates via `refresh_feed` and internal database operations. Your agent asks for the data, and the server serves cached or newly fetched entries depending on your query parameters.

Vinkius runs the MCP Server in an isolated V8 sandbox, meaning your API keys and RSS database credentials never persist on disk. All network traffic to your feed reader is encrypted, and the sandbox destroys itself after execution.

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