How to Use the Markdown Frontmatter Harvester MCP in Claude Code

Q: How do I add the Markdown Frontmatter Harvester to Claude Code?

Run claude mcp add --transport http markdown-harvester -- . Make sure all flags come before the server name so the CLI parses them correctly.

Q: Can I pipe the JSON output from Markdown Frontmatter Harvester in Claude Code to jq?

Yes. The harvestmarkdownfrontmatter tool outputs raw structured JSON, making it perfect for standard Unix text processing utilities.

Pipe your Obsidian metadata directly into terminal scripts with Claude Code.

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 Claude Code

Create your Vinkius account to connect Markdown Frontmatter Harvester to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless Vault CI/CD Pipelines

The Markdown Frontmatter Harvester MCP Server exposes your local knowledge base to terminal-based automation scripts. You can run automated checks against your Hugo content directory right from your command line. When you trigger Claude Code in a CI environment, it uses `harvest_markdown_frontmatter` to verify that all new blog posts have valid publication dates. If a draft slips through, the agent flags the commit before it merges.

Claude Code MCP Server Cron Jobs

This MCP Server turns thousands of scattered markdown files into a single parseable stream for your weekly note reviews. Automating your personal knowledge management requires fast metadata extraction. You set up a cron job that wakes up your CLI agent every Sunday. It runs `harvest_markdown_frontmatter`, filters the JSON for tasks tagged 'urgent', and pipes that list directly into a Slack webhook.

Migration and Schema Updates

Executing the Markdown Frontmatter Harvester on your vault path maps out your current tag structure for fast schema updates. Changing your personal knowledge management schema usually means writing tedious Python scripts. By calling `harvest_markdown_frontmatter`, the agent gets an exact list of files using deprecated fields. It then executes a batch `sed` command across your files to update those YAML keys instantly.

Setup guide

Set up Markdown Frontmatter Harvester MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see markdown-frontmatter-harvester-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Markdown Frontmatter Harvester transactions." It will automatically discover and invoke the available Markdown Frontmatter Harvester tools.

Terminal

claude mcp add --transport http markdown-frontmatter-harvester-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Markdown Frontmatter Harvester MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "markdown-frontmatter-harvester-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

Run `claude mcp add --transport http markdown-harvester -- `. Make sure all flags come before the server name so the CLI parses them correctly.

Yes. The `harvest_markdown_frontmatter` tool outputs raw structured JSON, making it perfect for standard Unix text processing utilities.

You likely provided a relative path. The tool requires an absolute directory path to correctly traverse your file system and locate the `.md` files.

It runs perfectly in containerized environments. Just mount your markdown directory as a volume and pass the internal absolute path to the tool.

The tool only reads the YAML frontmatter block at the very top of your `.md` files. Your actual paragraph text remains unread, and the CLI agent processes the extracted tags entirely within your local terminal session.

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