DEV Community: Du'An Lightfoot

How to Use MCP to Track Your DevRel Impact

Du'An Lightfoot — Tue, 26 Aug 2025 16:37:00 +0000

Every quarter, developer advocates like myself from across the industry face the same nightmare: review time. This can be yearly, quarterly, monthly, and when things are really bad weekly. When this happens your manager often asks that dreaded question, "So, what did you accomplish this month?" and suddenly you're panic-scrolling through browser history, Asana boards, emails and digging through old tweets while desperately trying to reconstruct 4 weeks or months worth of work from scattered digital breadcrumbs.

Sound familiar? After years of living this exact scenario, I decided enough was enough. Meet DevRel MCP - a comprehensive tracking system that transforms your career chaos into clear, actionable insights using the power of Model Context Protocol.

Why Tracking is Important

Here's a typical DevRel workflow: You create a viral YouTube video about AWS Lambda best practices. It gets great engagement. Three months later during your review, you vaguely remember the video existed but have no idea how many views it got, whether it generated leads, or what impact it actually had on your goals. Now apply this to speaking engagements, workshops and everything else you have done.

We've all been trapped in this cycle:

Content scattered everywhere — YouTube analytics, blog post metrics, social media insights all living in different silos
Events with no follow-up — You delivered an amazing conference talk, but what was the measurable impact beyond applause?
Manual metric hunting — Logging into 15 different platforms just to compile basic performance data
Zero trend analysis — Is your content strategy actually working? Are you getting better over time? Who knows!

The traditional solution is a messy spreadsheet that you forget to update for weeks, then abandon entirely by month two.

Enter the Model Context Protocol (MCP)

I wanted something that I could easily integrate into my existing workflow and be able to use an agent to analyze the data. Of course I could of built an app. But then I would actually have to build an agent along with everything else. After trying multiple solutions I finally realized that the Model Context Protocol, or MCP could be the right approach.

MCP servers let you extend AI assistants like Claude with custom tools and capabilities. Instead of context-switching between apps, I can now track my entire DevRel career using natural language right inside Claude Code or Claude Desktop:

You: "Track my new YouTube video about AWS Lambda best practices. 
     URL is youtube.com/watch?v=example123, it has 1,200 views and 89 likes."

DevRel MCP: ✅ Content tracked! Auto-detected tags: aws, lambda, serverless
            Ready for future metric updates and performance analysis.

No forms to fill out, no apps to remember, no friction whatsoever.

What DevRel MCP Actually Does for You

Content Tracking

Traditional approach: Manually log into YouTube Studio, then your blog analytics, then social media dashboards, copy numbers into a spreadsheet, repeat monthly.

DevRel MCP approach:

You: "I just published a blog post about serverless monitoring. 
     The URL is example.com/serverless-monitoring, got 500 views so far."

DevRel MCP: Creates comprehensive content record with auto-categorization,  
            smart tagging, and prepares for ongoing metric tracking

The system handles videos, blog posts, social content, documentation, podcasts, and code repositories. Everything gets automatically categorized and tagged based on your content, making future searches effortless.

Event Management Beyond Your Calendar

Your calendar tells you when and where. DevRel MCP tells you impact.

You: "I'm speaking at KubeCon next month. Workshop called 'Kubernetes Security 
     Deep Dive' at the Seattle Convention Center on March 15th."

DevRel MCP: Event created! Tracking location, audience size expectations,
            and prepared for post-event outcome analysis

After the event:

You: "KubeCon workshop update: 85 attendees, satisfaction score of 8.7/10, 
     generated 15 qualified leads, and booked 3 follow-up meetings."

DevRel MCP: Outcomes updated! ROI calculated including travel costs.
            Event marked as high-impact for future reference.

This transforms events from calendar entries into trackable business investments with measurable returns.

Analytics That Actually Tell Your Story

Here's where DevRel MCP moves beyond simple data storage into genuine career intelligence. The analytics engine doesn't just store numbers — it reveals patterns, calculates trends, and tells your professional story with data.

Quarterly Performance Analysis:

{
  "executive_summary": {
    "content_pieces": 12,
    "events_delivered": 8, 
    "total_reach": 47500,
    "leads_generated": 89
  },
  "growth_trends": {
    "views_growth_percentage": 34.2,
    "engagement_growth_percentage": 28.7,
    "content_volume_growth_percentage": 15.8
  }
}

Event ROI Analysis:

{
  "financial_summary": {
    "total_revenue": 12500.00,
    "total_costs": 4200.00,
    "net_revenue": 8300.00,
    "roi_percentage": 197.62
  },
  "impact_summary": {
    "total_attendees": 425,
    "total_leads_generated": 67,
    "avg_satisfaction_score": 8.4
  }
}

These may look like just numbers, but numbers don't like. And using this data is what can help you grow where you are or either somewhere else.

Real DevRel Workflows in Action

The Quarterly Review Hero

Before DevRel MCP: Spend three stress-filled hours the night before your review frantically reconstructing the quarter from memory, browser history, and prayer.

After DevRel MCP:

You: "Generate my Q3 quarterly report with export to CSV"

DevRel MCP: ✅ Report generated! 
- 12 content pieces reaching 45,000 people
- 8 events with 89% average satisfaction
- 156% content growth vs previous quarter  
- $12,000 net revenue from speaking
- Full CSV exported for your review meeting

Attach the professional report to your self-assessment and watch your manager's eyebrows raise in impressed surprise.

The Content Strategy Optimizer

You: "What's my best performing content from the last 6 months?"

DevRel MCP: Top 3 by engagement rate:
1. "AWS Lambda Cold Starts Explained" - 4.8% engagement, 12K views
2. "Serverless Security Checklist" - 4.2% engagement, 8K views  
3. "Infrastructure as Code Mistakes" - 3.9% engagement, 15K views

Pattern detected: Security and best practices content outperforms tutorials by 67%

Use these insights to double down on what actually resonates with your audience instead of guessing.

The Technical Foundation (For the Curious)

DevRel MCP is built on FastMCP, a Python framework that makes creating MCP servers straightforward. Here's whats under the hood:

Architecture Overview

20+ MCP Tools: From basic create_content to advanced generate_quarterly_report
TinyDB Database: Modern JSON-based document storage with native Python types
Advanced Analytics Engine: Performance calculations, trend analysis, ROI metrics
Privacy-First Design: Local storage, comprehensive .gitignore, no cloud dependencies
Export Capabilities: CSV and JSON formats for reporting and data portability

Key Technical Innovations

Flexible Input Handling: MCP can send data as strings or native types. DevRel MCP handles both seamlessly:

views: Union[str, int, None] = None  # Accepts "1500" or 1500
tags: Union[str, List[str], None] = None , Accepts "aws,lambda" or ["aws", "lambda"]

YouTube Integration: One command handles complete video tracking:

@mcp.tool()
def track_youtube_video(
    title: str,
    url: str, 
    views: Union[str, int, None] = None,
    likes: Union[str, int, None] = None
) -> Dict[str, Any]:
    # Auto-detects tags from title/description
    # Stores with full metadata for analytics

Smart Search: Full-text search across titles, descriptions, and AI-generated summaries:

You: "Find my content about MCP"
DevRel MCP: Found 3 items including video summaries and blog descriptions

The system runs entirely locally — your data never leaves your machine, and everything is git-safe by default.

Getting Started (3 Minutes to Impact Tracking)

1. Installation

git clone https://github.com/labeveryday/devrel-mcp
cd devrel-mcp
uv sync

2. Connect to Your AI Assistant

Claude Code:

claude mcp add devrel-mcp --scope user \
  -- uv --directory /path/to/devrel-mcp run src/server.py

Claude Desktop: Add to your configuration:

{
  "mcpServers": {
    "devrel-mcp": {
      "command": "uv",
      "args": ["--directory", "/path/to/devrel-mcp", "run", "src/server.py"]
    }
  }
}

3. Start Tracking Your Impact

You: "Track my recent conference talk about cloud security. 
     'Zero Trust Architecture for Serverless' at AWS re:Invent, 
     250 attendees, 9.1 satisfaction score."

DevRel MCP: Event tracked! Auto-tagged: aws, security, serverless, zero-trust
            Ready for ROI analysis and quarterly reporting.

That's it. You're now tracking your DevRel impact like a pro.

Why This Transformation Matters Now

Developer advocacy is evolving no matter how you look at it. DA's and DevRel for that matter are being told to show their value to an organization. One key way an advocate does this is through metrics. Random activity reports don't cut it anymore. It's time to track what you do so when the time comes you can use the data to show your real business impact.

DevRel MCP helps you:

Quantify actual impact with metrics that matter to business stakeholders
Identify successful patterns so you can replicate what works and abandon what doesn't
Professional reporting that positions you as strategic and data-driven
Career advancement by clearly demonstrating quantifiable value to your organization

In an industry where "influence" can feel abstract, being able to show your metrics become your career superpower.

Join the DevRel Analytics Revolution

It's open source, privacy-focused, and built by a developer advocate who has lived through every pain point you're experiencing.

Numbers are the difference between good DAs and great DAs. Start measuring your impact today.

Get started: github.com/labeveryday/devrel-mcp

Questions? I'd love to hear how you're currently tracking your DevRel impact and help you level up your analytics game.

Building the Ultimate Bookmark Manager with Amazon Q CLI and MCP

Du'An Lightfoot — Wed, 28 May 2025 17:05:00 +0000

The Problem: Information Overload

As developers, we're constantly saving links. And that's not a real problem. The problem arises when we are trying to recall that blog post that covers "How to configure MCP with Streamable HTTP inside of a Lambda function". Or if we are trying to list all of our bookmarks related to a specific topic. For me this has always been nothing but frustration.

The Solution

To solve this problem I built LinkVault, which is an open-source MCP server that allows you to integrate with AI Agents like Amazon Q CLI to provide AI-powered bookmark management. So, instead of building another standalone tool, you can use Natural Language in a conversational interface to manage your bookmarks.

Key Features

Amazon Q CLI Integration: Natural language bookmark management right in your terminal
MCP Server Architecture: Extends Amazon Q with custom bookmark management tools
Chrome Multi-Profile Support: Access bookmarks from all your Chrome profiles
Content Extraction: Automatically analyze and categorize webpage content
Cross-Platform: Works wherever Amazon Q CLI runs (macOS, Windows, Linux)

The Power of Model Context Protocol

The real innovation in LinkVault is how it uses the Model Context Protocol (MCP) to extend Amazon Q's capabilities. MCP allows Amazon Q to access external tools and data sources, effectively teaching it new skills.

When you register LinkVault as an MCP server with Amazon Q CLI, it gains the ability to:

Extract and analyze content from web URLs
Access your Chrome bookmarks across all profiles
Store, categorize, and tag bookmarks intelligently
Search across your entire bookmark collection using natural language

Amazon Q CLI in Action

Here's what the experience looks like in your terminal:

Checking if a bookmark exists.

$ q chat
Welcome to Amazon Q CLI!

> > Can you tell me if I have this bookmark stored? https://community.aws/content/2vzj07Wyk6Lw281Tvs1Lw7kJJNW/building-scalable-mcp-servers-on-aws-lambda-a-practical-guide?lang=en

I'll check if you have that bookmark stored. Let me search for it in your bookmarks.


🛠️  Using tool: search_bookmarks from mcp server bookmark_manager
 ⋮
 ● Running search_bookmarks with the param:
 ⋮  {
 ⋮    "arguments": {
 ⋮      "query": "https://community.aws/content/2vzj07Wyk6Lw281Tvs1Lw7kJJNW/building-scalable-mcp-servers-on-aws-lambda-a-practical-guide"
 ⋮    },
 ⋮    "name": "search_bookmarks"
 ⋮  }
Allow this action? Use 't' to trust (always allow) this tool for the session. [y/n/t]:

> t

 ⋮
 ● Completed in 0.3s
I've searched your bookmarks and couldn't find this URL:
https://community.aws/content/2vzj07Wyk6Lw281Tvs1Lw7kJJNW/building-scalable-mcp-servers-on-aws-
practical-guide

The search returned 0 results, which means this bookmark is not currently stored in your collection. Would
you like me to add it to your bookmarks?

Adding a new bookmark

> yes add it
I'll add that bookmark for you. Let me first get some information about the URL to create a proper bookmark
entry.


🛠️  Using tool: get_url_data from mcp server bookmark_manager
 ⋮
 ● Running get_url_data with the param:
 ⋮  {
 ⋮    "arguments": {
 ⋮      "url": "https://community.aws/content/2vzj07Wyk6Lw281Tvs1Lw7kJJNW/building-scalable-mcp-servers-on-aws-lambda-a-practical-guide"
 ⋮    },
 ⋮    "name": "get_url_data"
 ⋮  }
Allow this action? Use 't' to trust (always allow) this tool for the session. [y/n/t]:

> t

 ⋮
 ● Completed in 0.384s


🛠️  Using tool: store_url from mcp server bookmark_manager
 ⋮
 ● Running store_url with the param:
 ⋮  {
 ⋮    "arguments": {
 ⋮      "category": "AWS",
 ⋮      "description": "A practical guide on building scalable Model Context Protocol (MCP) servers using AWS Lambda and Lambda Web Adapter, covering implementation of sessionless Streamable HTTP communication, Lambda Function URLs, and performance optimization.",
 ⋮      "importance": 4,
 ⋮      "notes": "Useful resource for implementing MCP servers in a serverless architecture with AWS Lambda. Contains implementation steps, optimization tips, and best practices.",
 ⋮      "tags": [
 ⋮        "MCP",
 ⋮        "Lambda",
 ⋮        "Serverless",
 ⋮        "AWS",
 ⋮        "Model Context Protocol"
 ⋮      ],
 ⋮      "title": "Building Scalable MCP Servers on AWS Lambda: A Practical Guide",
 ⋮      "url": "https://community.aws/content/2vzj07Wyk6Lw281Tvs1Lw7kJJNW/building-scalable-mcp-servers-on-aws-lambda-a-practical-guide"
 ⋮    },
 ⋮    "name": "store_url"
 ⋮  }
Allow this action? Use 't' to trust (always allow) this tool for the session. [y/n/t]:

> t

 ⋮
 ● Completed in 0.3s
I've successfully added the bookmark to your collection:

• Title: Building Scalable MCP Servers on AWS Lambda: A Practical Guide
• URL: https://community.aws/content/2vzj07Wyk6Lw281Tvs1Lw7kJJNW/building-scalable-mcp-servers-on-aws-
lambda-a-practical-guide
• Category: AWS
• Tags: MCP, Lambda, Serverless, AWS, Model Context Protocol
• Importance: 4/5
• Date Added: 2025-05-28

The bookmark has been stored with a description that summarizes the article's content about implementing
MCP servers using AWS Lambda and Lambda Web Adapter. I've also added notes highlighting that it's a useful
resource for serverless MCP implementation with implementation steps and optimization tips.

This natural language interface makes bookmark management feel effortless for me since its right in my Amazon Q Cli daily workflow. Yes, I use it for everything! If you have questions on how I use it let me know in the comments and I will write a new post.

How MCP Makes It Possible

The Model Context Protocol is what enables this seamless integration. LinkVault exposes a set of tools to Amazon Q:

Multi-Profile Chrome Integration

One feature that I am working to improve is the ability for LinkVault to access bookmarks across all your Chrome profiles. If you're like me, you might have separate profiles for:

Work (AWS documentation, business IP, customer architectures)
Personal / Home (tech blogs, learning resources)
Development (code samples, GitHub repositories)

I've designed LinkVault to bring them all together in one unified interface.

NOTE: This feature will be improved to support Firefox and Safari soon.

Setting Up LinkVault with Amazon Q CLI

Getting started with LinkVault is straightforward:

Install Amazon Q CLI if you haven't already
Clone the LinkVault repository

git clone https://github.com/labeveryday/linkvault-mcp-server.git && cd linkvault-mcp-server

Install UV to manage your environment setup
Create a virtual environment

uv init
uv venv
source .venv/bin/activate

Install dependencies with uv install .
Register LinkVault as an MCP server in your Amazon Q configuration:

// ~/.aws/amazonq/mcp.json
{
  "bookmark_manager": {
    "command": "uv",
    "args": ["--directory", "/path/to/linkvault-mcp-server", "run", "src/server.py"],
    "env": {},
    "disabled": false,
    "autoApprove": ["get_url_data", "store_url", "search_bookmarks", "list_chrome_bookmarks"]
  }
}

Start a new Amazon Q CLI session and begin managing your bookmarks!

Building Your Own MCP Tools

The beauty of the Model Context Protocol is that it allows developers to extend Amazon Q CLI's and AI agent capabilities in countless ways. LinkVault is just one example of what's possible.

By following a similar pattern, you could build MCP servers that:

Connect Amazon Q CLI to your internal knowledge bases
Provide custom code generation capabilities
Enable interaction with specialized APIs
Create AI-powered interfaces to your development tools

What's Next for LinkVault?

I'm actively working on expanding LinkVault with:

Safari and Firefox browser support
Enhanced content analysis for better categorization
Integration with AWS service documentation
Collaborative bookmark sharing for teams
Host in AWS

Conclusion

LinkVault demonstrates the power of extending Amazon Q CLI through the Model Context Protocol. By connecting Amazon Q CLI to your browser bookmarks, it creates a natural language interface to your web research that fits seamlessly into your development workflow.

If you're an AWS developer looking to tame your bookmark chaos while staying in your terminal, give LinkVault a try. And if you're interested in building your own MCP tools, I hope this project provides some inspiration.

Have you built tools that integrate with Amazon Q CLI? I'd love to hear about your experiences in the comments!

This post was written by Du'An Lightfoot, Sr. Developer Advocate at AWS. The views and opinions expressed in this post are my own and don't necessarily represent the positions, strategies, or opinions of Amazon Web Services.