DEV Community: remoet.dev

Ghost Jobs: 30% of What You're Applying to Doesn't Exist

Carl-W — Mon, 13 Apr 2026 21:24:16 +0000

You applied to 100 jobs last month. About 30 of them didn't exist.

Not "the role was filled." Not "they went with an internal candidate." The job was never real. Nobody was ever going to get hired. The posting was there to serve a purpose that had nothing to do with you.

The numbers are worse than you think

27.4% of U.S. LinkedIn listings are ghost jobs. A Resume Builder survey found 3 in 10 companies have fake job postings live right now. Not by accident. On purpose.

81% of recruiters admit their employer posts roles that don't exist or are already filled. In tech, 40% of companies posted fake jobs in the past year. 79% of those are still up.

Los Angeles has a 30.5% ghost job rate. But it's not a local thing. It's everywhere.

Why companies do this

The reasons are almost never about hiring. That's the part that should piss you off.

Companies post jobs to look like they're growing. If you're raising a Series B and your careers page shows 40 open roles, investors see scale. Whether those roles are real doesn't matter. The perception is the product.

Some companies post jobs to do free market research. They want to see who applies, what salary expectations look like, how deep the talent pool goes in a given city. You spend 45 minutes on your application. They get a data point. Nobody was ever going to call you.

Others use ghost postings as a retention tool. "Look at all these open roles. We could replace you tomorrow." It's a threat dressed up as a careers page.

And then there's plain negligence. A role gets filled internally. Nobody turns off the auto-renew in the ATS. The posting sits there for 6 months collecting applications from people who think it's real. This is probably the most common one, and somehow it's also the most insulting. They couldn't even be bothered to click "close."

15 hours you're not getting back

Each application takes about 30 minutes when you actually do it right. Reading the description, adjusting your resume, writing responses, submitting. Apply to 100 jobs in a month, 30% are ghosts, that's 30 wasted applications. 15 hours. Gone.

But the time isn't the worst part.

You applied. You were qualified. You heard nothing. And you start wondering if you're the problem. Maybe your resume sucks. Maybe you need to learn another framework. Maybe you're too expensive. You internalize the rejection when there was nothing to be rejected from.

The job didn't exist.

72% of job seekers report negative mental health impacts from drawn-out hiring processes. Ghost jobs are a huge part of that. Every fake listing adds another false data point to your "maybe I'm not good enough" story.

How to spot them

None of these are guaranteed. But stacking them together filters out most of the garbage.

Check the posting date. If it's been up for 60+ days, especially at a tech company, something is off. Most real positions fill within 30-45 days. Three months? Either it's a ghost, the role is impossibly niche, or the company can't get their act together. None of those are encouraging.

Read the actual description. Ghost jobs are almost always vague. "Looking for a talented engineer to join our growing team." No tech stack mentioned. No team name. No specific project. Real hiring managers get specific because they need a specific person. Vagueness is a tell.

Look at the company's pulse. Are they active on social media? Have they made recent hires you can see on LinkedIn? Do they have an engineering blog that's been updated this year? A company listing 20 open roles with zero public activity for 4 months is suspicious.

Cross-reference the source. If a job shows up on Indeed, LinkedIn, Glassdoor, and three other boards but isn't on the company's own careers page, it's a stale aggregation. Some distribution service is auto-syndicating a dead listing that nobody bothered to kill.

Job boards won't fix this

Job boards make money from listings. More listings means more page views. More page views means more ad revenue or higher subscription fees. A ghost job and a real job generate the same engagement metrics.

Indeed, LinkedIn, Glassdoor. None of them have an incentive to remove ghost postings. The ghost job is doing exactly what their business model needs. Just not what you need.

The platforms you trust to help you find work are economically rewarded for keeping fake listings live. That's a broken foundation and no amount of UI polish fixes it.

Regulation is coming, slowly

Ontario passed legislation requiring companies to disclose whether a posting is for a real, active vacancy. The U.S. has the TJAAA bill working through Congress with similar requirements.

When lawmakers write bills specifically about fake job postings, the problem has gone past "industry nuisance" into "systemic failure." But regulation is slow. Enforcement is slower. You can't wait for Congress to fix your job search.

Stop searching for jobs. Start tracking companies.

Sounds backwards. But think about it.

The ghost job problem exists because you're interacting with listings, not companies. A listing can be fake. A company can't fake its existence, its tech stack, or whether it's actually made hires recently.

Pick 10-20 companies where your tech stack genuinely overlaps. Track them. Watch for new roles at those specific companies. When one of them posts something, you know it's more likely to be real because you've been watching the company, not a random feed of disconnected listings.

This is what I built Remoet around. 725+ remote tech companies, tracked, with real tech stack data. You star the ones that match your skills, and your AI agent monitors them for you. It doesn't eliminate ghost jobs entirely. Some companies will always play games. But you go from fishing in a pool that's 30% fake to watching a handful of companies you've already vetted.

Apply fewer. Apply better.

The instinct when you learn about ghost jobs is to compensate with volume. "If 30% are fake, I'll just apply to 3x as many." That's the trap. More volume means more time wasted on ghosts, more silence, more false rejections eating at your confidence.

The opposite works. Narrow your target. Verify the company is real and active. Check the posting date. Look at the tech stack. Then apply once, with effort, to something that's actually there.

30% of what you're applying to doesn't exist. The fix isn't applying harder. It's not applying to bullshit.

Frequently Asked Questions

What is a ghost job?

A ghost job is a posting for a position that isn't actually open or that the company never intends to fill. It exists for other reasons: signaling growth to investors, collecting market data, pressuring existing employees, or just negligence where nobody closed the listing after the role was filled internally.

How common are ghost jobs?

Between 27-30% of job listings, depending on the study. Resume Builder found 3 in 10 companies currently have fake postings live. In tech specifically, 40% of companies posted at least one fake job in the past year, and 79% of those are still active.

How do I know if a job posting is fake?

Look for a combination of red flags: the posting has been up for 60+ days, the description is vague with no specific tech stack or team, the same listing appears on aggregator sites but not on the company's own careers page, and the company shows no other signs of active hiring (no recent LinkedIn hires, no social media activity).

Are ghost jobs illegal?

In most places, not yet. Ontario passed legislation requiring disclosure of whether a posting is for an active vacancy. The U.S. has the TJAAA bill in Congress. Regulation is moving, but slowly.

Why don't job boards remove ghost jobs?

Because ghost jobs make them money. A fake listing generates the same page views, ad impressions, and engagement metrics as a real one. The platforms have no economic reason to clean them up.

What Is MCP (Model Context Protocol)? A Practical Guide

Carl-W — Wed, 25 Mar 2026 11:21:58 +0000

MCP (Model Context Protocol) is an open standard that lets AI agents connect to external software, discover available tools, and take actions on your behalf. Instead of being trapped in a chat window, your AI can search databases, manage projects, update profiles, and interact with any service that runs an MCP server.

You've probably seen MCP mentioned everywhere lately. Twitter threads, blog posts, product announcements. Every AI company seems to be shipping an "MCP server" and every developer tool is adding "MCP support." But if you've tried to figure out what MCP actually is, you've probably run into a wall of jargon and protocol specs.

I'm going to cut through that.

MCP in Plain English

Anthropic introduced MCP in November 2024. In December 2025, they donated it to the Agentic AI Foundation under the Linux Foundation, with OpenAI, Block, and others as co-stewards. It's a genuinely open protocol now.

Here's the problem it solves. When you use Claude or ChatGPT, the AI can talk to you, but it can't actually do anything outside that conversation. It can't check your calendar, search a database, file a bug report, or look up your job applications. It's stuck inside a text box.

MCP changes that. It's a universal plug that lets an AI agent reach into other software and take actions on your behalf. Search a job board. Update a project. Star a company. Send a message. Whatever the connected service supports.

Yeah, I know, the USB analogy is the cliche everyone uses for MCP. But it's accurate, so I'll use it anyway: before USB, every device had its own proprietary connector. Printers, keyboards, cameras, all different cables. USB standardized the physical connection. MCP standardizes the AI-to-software connection.

How It Actually Works

Under the hood, MCP uses JSON-RPC 2.0 as its wire protocol. If you've worked with LSP (Language Server Protocol), the architecture will feel familiar. There are two sides to every MCP connection:

The client is your AI agent. Claude Desktop, Cursor, Windsurf, Claude Code, Cline. These are the apps where you type prompts and have conversations. They speak MCP natively.

The server is whatever tool or service you want the agent to access. A GitHub MCP server lets your agent manage repos and issues. A Notion MCP server lets it read and write documents. A Remoet MCP server lets it search remote job listings, manage your developer profile, and track applications.

When a client connects to a server, the server advertises its capabilities through three primitives:

Tools: Actions the agent can execute. Searching listings, creating a profile entry, submitting an application. These are the most commonly used primitive.
Resources: Data the agent can read, like files, database records, or configuration. Think of these as GET endpoints.
Prompts: Predefined templates that guide the agent through specific workflows. Less common but useful for complex multi-step tasks.

Each tool has a name, a description, and a JSON Schema defining its inputs. The AI reads those descriptions and figures out which tools to call based on what you ask.

So when you say "find me remote companies hiring React developers," the agent looks at the available tools, picks the search tool, fills in the right parameters, calls it, and returns the results. You never have to know the tool exists. You just describe what you want.

MCP vs Function Calling

This is the confusion I see most often. Function calling is a model-level feature where the AI can output structured JSON to invoke predefined functions. It's been around since 2023. MCP is the transport and discovery layer that sits on top of function calling.

Think of it this way: function calling is the engine. MCP is the road network.

Without MCP, every developer has to manually define function schemas, wire them up to API clients, handle authentication, and build the plumbing for each integration from scratch. MCP standardizes all of that. The server describes its tools once, any MCP client can discover and use them, and the client's function calling capability handles the actual invocation.

So they're complementary, not competing. Function calling is what lets the model decide to call a tool. MCP is what lets the model discover tools dynamically from external servers and execute them over a standardized transport.

MCP vs A2A (Agent-to-Agent Protocol)

Google released their Agent-to-Agent (A2A) protocol in early 2025, and I keep seeing people ask whether it competes with MCP. Short answer: no. They solve different problems.

MCP connects an agent to tools and data. A2A connects an agent to another agent. MCP is about giving one agent hands to interact with software. A2A is about letting multiple agents collaborate with each other on a task. You'd likely use both in a mature agentic system, with MCP for tool access and A2A for multi-agent coordination.

The Three Primitives in Practice

I mentioned Tools, Resources, and Prompts above, but it's worth seeing how they play out in a real MCP server.

Remoet has 38 MCP tools. When your agent connects, it receives all 38 tool definitions with their descriptions and parameter schemas. The agent doesn't need documentation. It reads the tool descriptions and figures out the right calls.

Ask "find companies using Go and Kubernetes" and the agent picks the search tool. Ask "show my applications" and it picks the applications tool. Ask "update my summary" and it picks the profile update tool. All from the same conversational interface. No menus, no navigation, no context switching.

This is fundamentally different from a traditional API integration. With an API, a developer writes code to call specific endpoints with specific parameters. With MCP, you describe your intent in natural language and the AI handles the rest.

Security: OAuth 2.1, PKCE, and Prompt Injection

I won't sugarcoat this: connecting AI agents to live services introduces real security considerations.

On the authentication side, MCP supports OAuth 2.1 with PKCE (Proof Key for Code Exchange). This is the same security standard used by major web applications. Each connection requires explicit user authorization, and you can revoke access at any time. Remoet's MCP implementation enforces PKCE on every authorization, with session limits and LRU eviction to prevent resource exhaustion.

The trickier risk is prompt injection. If an MCP server returns malicious content in tool results, it could theoretically trick the agent into taking unintended actions. Good MCP implementations mitigate this by treating all tool results as untrusted data (Remoet's server description explicitly instructs agents to do this), but it's an active area of research. The MCP spec itself is evolving to add better guardrails here.

If you're evaluating MCP servers, look for ones that use OAuth 2.1 rather than just API keys, enforce PKCE, and document their approach to prompt injection defense.

Who Supports MCP Today

The ecosystem has grown fast. Thousands of MCP servers are now listed across various directories, and the number is climbing weekly.

On the client side:

Claude Desktop and Claude Web have native MCP support, including custom connectors via OAuth
Claude Code supports MCP servers out of the box via the CLI
Cursor has built-in MCP configuration
Windsurf supports MCP servers in its settings
VS Code now has native MCP support through GitHub Copilot
Cline and Continue also support MCP

On the server side, the ecosystem spans every category:

Category	Examples
Development	GitHub, Linear, Sentry
Productivity	Notion, Slack, Google Drive
Data	Supabase, PostgreSQL, various database connectors
Search	Brave Search, Context7 (documentation search)
Career & Jobs	Remoet (remote job search, profile management, applications)
Automation	n8n, Zapier

What's striking is that MCP servers aren't just developer tools anymore. They're showing up in every vertical: job platforms, finance tools, CRM systems, e-commerce. Any software with an API can become an MCP server, and increasingly, they are.

Why This Matters For You

If you're a developer, MCP means you can automate a huge chunk of your workflow through conversation. Instead of context-switching between 15 browser tabs, you tell your agent what you need and it handles the tool-hopping.

If you're job hunting, this is where it gets genuinely interesting. Traditional job boards make you do all the work: search, filter, scroll, click into each listing, apply one by one. An MCP-connected job platform flips that. You tell your agent "find companies using my tech stack that are actively hiring" and it does the searching, filtering, and shortlisting for you.

That's exactly what Remoet does. Connect your AI agent once, and it handles the rest: finding companies that match your stack, tracking applications, messaging hiring teams. Your agent becomes your career assistant.

But beyond any single platform, the bigger shift is this: software is becoming conversational. Instead of learning each app's UI, you describe what you want and your agent navigates the tools for you. MCP is what makes that possible at scale.

Getting Started

If you want to try MCP yourself, the setup is simpler than you'd expect. Most MCP-compatible AI apps let you add servers through a configuration file or settings page. You typically need an API key or OAuth authorization from the service you want to connect, and then you're up and running.

We've got a detailed setup guide covering Claude Desktop, Claude Code, Cursor, and Windsurf in our post on how to set up MCP servers.

For a complete walkthrough of what AI-powered job search looks like in practice, check out our agent job search guide.

Frequently Asked Questions

Is MCP only for Claude?

No. MCP is an open protocol governed by the Linux Foundation. While Anthropic created it, it's been adopted by Claude, Cursor, Windsurf, VS Code, Cline, Continue, and others. Any AI client can implement MCP support. OpenAI added MCP support to their agents SDK in early 2025.

Do I need to be a developer to use MCP?

Not necessarily. Some setups require editing a JSON config file, which is a bit technical. But Claude Web supports custom MCP connectors through a point-and-click OAuth flow that requires zero coding. Desktop Extensions are also making one-click installs possible. The trend is clearly toward making MCP accessible to everyone.

Is MCP secure?

MCP supports OAuth 2.1 with PKCE for authentication, which is the same security standard used by major web applications. Each connection requires explicit authorization. You control which services your agent can access and can revoke access at any time. The main emerging concern is prompt injection through tool results, which is an active area of research in the MCP community.

What's the difference between MCP and a browser extension or plugin?

Browser extensions and plugins are specific to one application. A Chrome extension only works in Chrome. A ChatGPT plugin only worked in ChatGPT (and OpenAI deprecated them). MCP is standardized across all compatible AI clients. Build one MCP server and it works with Claude, Cursor, Windsurf, VS Code, and any future client that supports the protocol. Build once, work everywhere.

How many MCP servers can I connect at once?

There's no hard protocol limit. You can connect as many MCP servers as your AI client supports. Most people connect 3 to 10 servers depending on their workflow, covering things like code management, documentation, search, and whatever domain-specific tools they need.