How to Use the Markdown Frontmatter Harvester MCP in CrewAI

Equip your CrewAI agent teams with the tools to scan, filter, and organize local Obsidian and Hugo frontmatter.

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 CrewAI

Create your Vinkius account to connect Markdown Frontmatter Harvester to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Vault Analysis for CrewAI Teams

Assign a specialized research agent to scan your Obsidian vault while an editor agent analyzes the findings. The research agent uses `harvest_markdown_frontmatter` to pull all YAML metadata into shared memory. Once the JSON is in memory, the editor agent filters notes by tags or dates to find gaps in your documentation. This division of labor keeps your local knowledge base clean without manual searching.

Multi-Agent Content Planning with this MCP Server

Build a crew that manages your static site content pipeline. Your planning agent calls `harvest_markdown_frontmatter` to inspect the publication dates and tags of your Hugo markdown files. A separate writer agent then identifies which topics are outdated based on those YAML dates. This MCP Server provides the raw data that feeds your crew's entire content strategy.

Hierarchical Note Moderation

Use a manager agent to oversee a team of note-cleaning agents. The manager runs `harvest_markdown_frontmatter` to get a bird's-eye view of your entire directory structure and metadata health. The manager then delegates specific subfolders to worker agents based on which files have missing tags or broken YAML blocks. This structured execution keeps large vaults organized automatically.

Setup guide

Set up Markdown Frontmatter Harvester MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Markdown Frontmatter Harvester tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Markdown Frontmatter Harvester Analyst",
    goal="Access and analyze Markdown Frontmatter Harvester data via MCP.",
    backstory="Expert analyst with direct Markdown Frontmatter Harvester access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Markdown Frontmatter Harvester transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Markdown Frontmatter Harvester Analyst",
        goal="Access and analyze Markdown Frontmatter Harvester data via MCP.",
        backstory="Expert analyst with direct Markdown Frontmatter Harvester access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Markdown Frontmatter Harvester transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can pass the Vinkius MCP endpoint directly to your agent's configuration during initialization. CrewAI automatically discovers the `harvest_markdown_frontmatter` tool and makes it available to the agent.

No, this MCP Server is strictly read-only for metadata extraction. Your crew can analyze the YAML frontmatter to plan edits, but they cannot modify your files using this specific tool.

The tool outputs a structured JSON array of your vault's frontmatter. CrewAI places this output into its shared memory space, allowing all agents in the crew to query the same metadata dataset.

If your vault has thousands of files, the compiled JSON can be quite large. You should instruct your manager agent to filter the metadata array before passing it to subordinate agents.

All file scanning and extraction happen inside your secure sandbox, touching only the markdown metadata headers of your files. The actual content of your articles is never processed or uploaded.

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