How to Use the Markdown Frontmatter Harvester MCP in Vercel AI SDK

Feed structured Obsidian metadata directly into Vercel AI SDK stream without parsing delays.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Markdown Frontmatter Harvester MCP to Vercel AI SDK

Create your Vinkius account to connect Markdown Frontmatter Harvester 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 Markdown Frontmatter Harvester with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Instant Vault Aggregation for UI Streams

Your React frontend shouldn't freeze while your app parses thousands of local notes. Call the `harvest_markdown_frontmatter` tool to instantly compile all Hugo or Obsidian YAML headers into a single, clean JSON payload. Because Vercel AI SDK streams tool calls in real-time, your users watch the metadata populate their dashboard instantly. No loading spinners, just raw data hitting the Edge function and rendering on screen immediately.

Edge-Compatible Metadata Queries with this MCP Server

Running heavy file system searches inside Edge functions is a recipe for timeouts. This MCP Server solves that by offloading the heavy directory traversal and YAML parsing to the local server, returning a lightweight JSON array. You feed that structured output straight to `streamText` or `generateText`. Your TypeScript code gets clean, typed frontmatter objects containing tags, dates, and status fields without writing custom parser code.

Live Tag Filtering in Next.js

Let your users filter their personal wiki using natural language. The `harvest_markdown_frontmatter` tool reads the entire directory structure, extracts every tag, and hands it to the LLM to filter. The Vercel AI SDK UI helpers grab the returned JSON and update the client-side state immediately. You get instant UI updates based on the actual frontmatter of your local Markdown files.

Setup guide

Set up Markdown Frontmatter Harvester 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 Markdown Frontmatter Harvester 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 Markdown Frontmatter Harvester 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 gray-matter. 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 Markdown Frontmatter Harvester 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 Markdown Frontmatter Harvester MCP in Vercel AI SDK

Install the MCP package and create an HTTP client pointing to your Vinkius endpoint. Pass the tools from your client directly to your generateText call, and remember to close the connection when the stream ends.

Yes, the server isolates parsing errors so one bad Hugo file doesn't crash your Next.js stream. It skips broken blocks and returns valid JSON for the rest of your vault.

No, because the file scanning happens on the Vinkius-hosted MCP Server rather than inside your serverless runtime. Your Edge function simply receives the final structured JSON payload.

The tool compiles the metadata into a single array. If your vault is massive, you may want to filter the JSON on the server side before passing the final token-heavy payload to your LLM context.

We only process the YAML metadata block and local file paths, never reading your actual note body text. Your data is handled in an ephemeral V8 sandbox that destroys itself after the run.

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