From PDF to MCP: Let AI Agents Query Your Resume On Demand

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant

Leeson Wong · 2026-05-01 · via DEV Community

<h2> The Problem </h2> More and more companies are using AI for resume screening. HR hands the JD to an Agent, and the Agent matches candidates. But resumes are essentially PDFs (or web pages) — hard for AI to parse cleanly. Layout noise, scattered information, no structured querying. So I asked myself: why not make my resume AI-native? Not "AI-friendly" marketing fluff, but something an AI Agent can actually connect to, query on demand, and run structured analysis against. I built exactly that: a MCP Server for my resume. Visit the public page, and an AI Agent can auto-discover the endpoint, connect, search through experience, analyze job fit, and query skill proficiency. The project is open source: <a href="https://github.com/Leeson-Wong/resume-maker" rel="noopener noreferrer">github.com/Leeson-Wong/resume-maker</a> This article won't oversell the technical implementation (honestly, it's basic). Instead, let's talk about what the Resume + MCP combination actually means. <h3> What is MCP? </h3> MCP (Model Context Protocol) is an open protocol proposed by Anthropic that lets AI Agents connect to external data sources and tools in a standardized way. Think of it as "the API for the AI era" — except MCP is self-describing (tools come with name, description, inputSchema), so AI Agents can automatically understand how to use them without integration docs. <h2> See It in Action </h2> Here's what a recruiter's AI Agent can do after connecting: Query: Search for big data related experience <div class="highlight js-code-highlight"> <pre class="highlight javascript"><code>search_resume({ query: "big data" }) → Returns: relevant experience snippets + source modules + relevance scores </code></pre> </div> Query: Is this candidate a fit for our role? <div class="highlight js-code-highlight"> <pre class="highlight javascript"><code>evaluate_fit({ job_description: "\"Senior full-stack engineer, 5+ years, React/Node.js," big data platform experience, DevOps" }) → { score: 82, matched: ["react", "node", "big data", "devops", ...], missing: ["Kubernetes"], recommendation: "Strong match! ..." } </code></pre> </div> Query: Give me a comprehensive assessment <div class="highlight js-code-highlight"> <pre class="highlight javascript"><code>get_career_summary({}) → { seniority: "senior", totalYears: 6, domains: ["Big Data Cloud Services", "Cross-platform Development", "Indie Product Development"], coreStrengths: ["Multi-stack adaptability", "Independent product delivery", "AI protocol design"], topSkills: [{ name: "React", level: 4, yearsUsed: 5 }, ...] } </code></pre> </div> All structured JSON — no PDF parsing, no web scraping. The AI Agent processes data programmatically. <h2> The Key Insight Isn't Technical — It's Product Logic </h2> <h3> The Resume Submission Flow Has Changed </h3> Old flow: Send PDF → HR skims manually → Maybe passes to AI for辅助判断 New flow: Give HR a link + invite code → Their AI Agent connects via MCP → The Agent decides what to query and how to analyze The difference: the initiative shifts from HR to the AI Agent. The Agent queries dynamically based on what it cares about, rather than passively reading a fixed-format document. <h3> Invite Code = Reverse Filtering </h3> This is my favorite part of the design. When applying, you give HR a "link + invite code." HR needs to configure the invite code in their AI client before the Agent can access deep information. The process itself is a filter: teams without sufficient AI literacy can't even get through it. If they can, it means they're already using AI Agents in their hiring process — likely a more modern team. Plus, the invite code supports tracking — you can see exactly which tools the other party's Agent queried and when. Far more valuable than a "resume viewed" notification. You know what they actually care about. <h3> Privacy Tiers </h3> Public page and MCP responses expose different levels of information: <div class="table-wrapper-paragraph"><table> <thead> <tr> <th>Tier</th> <th>What's visible</th> <th>Channel</th> </tr> </thead> <tbody> <tr> <td>Public</td> <td>Name, title, skill tags, work history</td> <td> <code>/</code> public page</td> </tr> <tr> <td>MCP Query</td> <td>Project details, skill proficiency, fit analysis</td> <td> <code>/mcp</code> (invite code required)</td> </tr> <tr> <td>Private</td> <td>Email, phone number</td> <td>Never exposed via MCP</td> </tr> </tbody> </table></div> Not everything should be AI-accessible. Contact info belongs in the human communication phase. <h2> Three-Layer Discovery Mechanism </h2> How does an AI Agent know your resume has an MCP service? This is the most critical design decision — discovery matters more than connection. <div class="highlight js-code-highlight"> <pre class="highlight plaintext"><code>AI Agent visits https://your-domain.com ↓ Parses HTML, discovers <link rel="mcp" href="/mcp"> ↓ Requests /.well-known/mcp for full metadata (tool list, auth method) ↓ Connects using invite code via Authorization header ↓ Starts querying </code></pre> </div> Three layers of discovery, shallow to deep: Layer 1: HTML Injection — Auto-injected into public page, zero maintenance cost <div class="highlight js-code-highlight"> <pre class="highlight html"><code><link rel="mcp" href="/mcp"> <link rel="llms-txt" href="/llms.txt"> <script type="application/ld+json"> { "@type": "Person", "name": "...", "knowsAbout": [...] } </script> </code></pre> </div> Layer 2: /.well-known/mcp — Standard well-known endpoint, machine-readable full MCP config <div class="highlight js-code-highlight"> <pre class="highlight json"><code>{ "mcp": { "endpoint": "/mcp", "transport": "http", "auth": { "type": "bearer" }, "tools": [...] } } </code></pre> </div> Layer 3: /llms.txt — Follows the <a href="https://llmstxt.org/" rel="noopener noreferrer">llms.txt</a> standard, Markdown-formatted AI-friendly description All three layers are auto-generated server-side from the same <code>resume.json</code>. Update your resume, and all discovery info updates automatically. <h2> Architecture </h2> This is a self-hosted full-stack application, not SaaS. Single-user, deployed on your own server. <div class="highlight js-code-highlight"> <pre class="highlight plaintext"><code>/ → Public page (visible to anyone, MCP discovery info injected) /mcp → MCP endpoint (invite code auth, for AI Agents) /edit → Resume editor (auth code protected, for yourself) </code></pre> </div> Core principle: single source of truth — <code>resume.json</code>. Editor and MCP share the same data. MCP reads fresh data on every request — no cache staleness. The tech stack is nothing to brag about: React 19 + Vite 7 + Tailwind 4 for the editor, vanilla Node.js HTTP for the server, MCP SDK for the protocol layer, Zod for data validation. Search uses a hand-rolled TF scorer + mixed Chinese/English tokenization — good enough for keyword matching, nowhere near real semantic search. 8 tools total: <div class="table-wrapper-paragraph"><table> <thead> <tr> <th>Tool</th> <th>What it does</th> </tr> </thead> <tbody> <tr> <td><code>get_profile</code></td> <td>Public info, privacy fields never via MCP</td> </tr> <tr> <td><code>get_experience</code></td> <td>Work history, filterable by keyword</td> </tr> <tr> <td><code>get_projects</code></td> <td>Projects, filterable by tech stack</td> </tr> <tr> <td><code>get_skills</code></td> <td>Skill list with proficiency and years</td> </tr> <tr> <td><code>get_education</code></td> <td>Education background</td> </tr> <tr> <td><code>search_resume</code></td> <td>Full-text search, TF relevance scoring</td> </tr> <tr> <td><code>evaluate_fit</code></td> <td>Given a JD, outputs match score + missing skills</td> </tr> <tr> <td><code>get_career_summary</code></td> <td>Career overview: seniority, domains, core strengths</td> </tr> </tbody> </table></div> Each tool supports <code>format: 'text' | 'json'</code> — text for humans, json for programs. <h2> Engineering Decisions Worth Mentioning </h2> Atomic writes instead of a database — Resume data is ~2KB. Even SQLite feels overkill. write-to-temp + rename is atomic, plus a write queue for concurrency safety. Fresh MCP Server per request — Instead of a long-lived MCP Server created at startup, each request calls <code>createMcpServer(currentResume)</code>. This guarantees the latest data — edits are immediately visible to MCP. Zod schema validation — Validate on both read and write. The frontend editor validates too, but never trusting client input is basic hygiene. stdio mode — Besides HTTP, supports <code>start:stdio</code> for direct Claude Desktop configuration. No server needed for local development. <h2> Deployment </h2> <div class="highlight js-code-highlight"> <pre class="highlight shell"><code># One-command Docker deployment cp config.example.json config.json # Set your authCode docker compose up -d </code></pre> </div> Or connect directly via Claude Desktop: <div class="highlight js-code-highlight"> <pre class="highlight json"><code>{ "mcpServers": { "resume": { "command": "npx", "args": ["tsx", "server/stdio.ts"], "cwd": "/path/to/resume-maker" } } } </code></pre> </div> <h2> Honest Take </h2> The search and matching algorithms in this project are honestly mediocre. TF scoring is just keyword frequency counting, skill normalization is a lookup table, and evaluate_fit's matching logic is essentially string containment checking. These are far from "precisely understanding personal data." But the interesting part isn't the implementation. What's interesting is the new possibilities created by the Resume + MCP combination: <ol> <li> Information access has changed — From "reading a fixed document" to "AI querying structured data on demand"</li> <li> Filtering logic has changed — Invite codes reverse-filter recruiters by their AI literacy</li> <li> Data ownership has changed — Data lives on your own server, you control who sees what</li> </ol> These three shifts have nothing to do with implementation complexity. They're innovations at the product form level. MCP is still early — almost no recruiters are actually using AI Agents to connect to MCP endpoints. But the direction is right. As AI becomes more involved in hiring, resumes should evolve from "documents for humans" into "data sources for AI." If you're also experimenting with MCP, or interested in "AI-native personal information presentation," let's connect. Live Demo: <a href="http://47.97.101.194:965" rel="noopener noreferrer">http://47.97.101.194:965</a> (Invite code: <code>qm8vvf</code> — connect to the MCP endpoint to try all tools) Project: <a href="https://github.com/Leeson-Wong/resume-maker" rel="noopener noreferrer">github.com/Leeson-Wong/resume-maker</a> If you find it interesting, a Star would be appreciated. <h2> Another Project: BrickLife </h2> Quick shoutout to another thing I built — a simulation/management mini-game called "BrickLife" Play: <a href="http://47.97.101.194" rel="noopener noreferrer">http://47.97.101.194</a> (Best experience on mobile) <blockquote> This article was co-written with Claude Code + GLM-5.1. </blockquote>

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。

推荐订阅源

DEV Community