It's open.

Plug your AI agent into Remoet and let it do the boring half of looking for work. Searching the whole job board. Searching companies that match your stack. Filtering by salary, location, remote policy, whatever you care about. Saving the good ones with notes. Updating your profile, work history, and projects through conversation.

You stop clicking. You start prompting.

The server is live in production today, and it's free. There are no paid tiers for job seekers, so the limits further down are what every account gets.

(This post went up the day the server opened, and it has been kept current since rather than left to rot into a museum piece. Two things changed in a big way: the job catalogue went public, so your agent searches every role on the board without starring anything, and search_jobs grew the same filters the board has. The snippets below are the ones I'd paste today.)

If you missed the priming email

Quick recap. Remoet is a job platform built for the agent era. Companies and jobs are the data, but the way you interact with that data is your AI agent. Instead of bouncing between tabs, you talk to the agent you already use, and it talks to Remoet on your behalf.

The bridge that makes that possible is MCP, the Model Context Protocol. It's the open standard that lets AI clients like Claude, Cursor, Codex and ChatGPT connect to external tools and call them on your behalf. If MCP is new to you, start here. If it's not, the only thing you need to know about Remoet's implementation is the URL and the API key.

What you can actually do today

I want to be careful here because there's a lot of MCP marketing copy floating around that overpromises. Here's the real list. These all work.

Find companies by your stack. Tell your agent the technologies you care about. It searches Remoet's catalogue, returns the companies that overlap, and ranks them by job count or alphabetically or however you ask. Tech stack on Remoet is per-company, scraped and enriched from the roles each company is actually hiring for, not a tag a marketer wrote. That's the part nobody else has.

Search the whole job board. Every scraped role at remoet.dev/jobs is readable through search_jobs, with no account at all: every company, no star needed and none spent. It filters on free text, tech stack (any of them, or every one of them on the same role), company, location, remote policy, experience level and minimum salary, and sorts by newest or salary. If a search comes back empty, it tells you which filter emptied it and how many roles dropping that one filter would return.

Star the ones you'd actually work for. Quick clarification since "star" sounds like it should gate something: it doesn't, every role stays searchable with zero stars. What starring turns on is delivery. That company's new roles start landing in your feed and the roundup email, and the three-technology teaser opens up into the full stack. One star is enough to start: star a single company you'd seriously work for and the loop already works, the agent pulls that company's jobs, ranks them, you read what matters. Star ten and it just covers more ground. The point is to be selective, not to fill a number.

Pull jobs from your starred companies. The same filters as the open board, scoped to your shortlist, with sorting by recency or salary. The agent paginates, summarizes, ranks. You read the ones it surfaces. This is the loop most users run.

Save the good ones with notes. Same as the in-app save action, but the agent does it. "Save this one as a strong yes, note that the Go salary band is below my floor but the team looks great." Read those back later.

Manage your profile by talking. Update your summary. Add work experience. Add a project. Add education. Edit a link. Your agent reads what you tell it, normalizes the dates and structure, and writes it back. The classic "I should update my profile but I never do" problem solves itself when the cost of an update drops to one sentence.

Spin up link trees. Up to ten per account. The dev-flavored Linktree-style page that lives at remoet.dev/t/your-slug, sourcing from your profile data so it stays current.

There are more tools than that. I'm not going to count them in a blog post because the number drifts, and a number that drifts is how a post starts lying. The above is the daily-driver shape.

What does not work yet

I'd rather you find this out from me than from a tool error.

You cannot apply to most jobs through the agent. Almost every job in Remoet right now is scraped from a company's external careers page. The agent can find the job and hand you the link, but the actual application happens on the company's site like always. Internal applications, where you apply through Remoet end to end, only work for companies posting directly through our partner system.

Application records are not an agent surface yet. The tools that read and update them exist in the code but are not listed to agents. What your agent can do today is save a role and attach a note to it, which is where "I applied to this one on Tuesday" should go for now.

There's no cover-letter writing tool. Not yet. The plumbing exists, the front-end's not finished, so the MCP path skips it.

There's no GitHub integration. Your tech stack is what's in your Remoet profile, not what's actually in your repos. If you've never filled in your stack, the agent has nothing to match against. Take five minutes, fill it in, and the rest gets a lot smarter.

The board covers cleared ATS platforms only. Lever, Greenhouse, Ashby, Recruitee and Workable. A company hiring somewhere else does not turn up in the scrape.

That's the honest version. Everything else in the platform UI works at a similar level through the agent, with these gaps.

How to connect

Five minutes if you've used MCP before. Ten if you haven't. The setup guide has one working config per client and stays more current than any snippet frozen into a launch post; here is the short version.

1. Generate an API key

Sign in at remoet.dev/onboarding?mode=agent and a key is created for you on that page. It's a 32-character hex string. Manage or revoke keys later at remoet.dev/agents. Don't paste it anywhere shared.

2. Drop the config into your agent

Claude Code. Add the server with the CLI:

claude mcp add --transport http --scope user remoet https://api.remoet.dev/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

Start a new session afterwards.

Cursor. In ~/.cursor/mcp.json (or your project's .cursor/mcp.json for project-scoped):

{
  "mcpServers": {
    "remoet": {
      "url": "https://api.remoet.dev/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Reload Cursor.

Codex. One line: codex mcp add remoet --url https://api.remoet.dev/mcp --bearer-token-env-var REMOET_API_KEY.

Windsurf, now Devin Desktop. Same idea in ~/.codeium/windsurf/mcp_config.json, where the URL field is called serverUrl.

Claude Desktop and claude.ai. No API key, no JSON. Customize > Connectors > Add custom connector, pointed at:

https://api.remoet.dev/mcp/oauth

Claude walks you through the sign-in. This is the lowest-friction path if you don't want to mess with config files. Note the URL: the plain /mcp endpoint is for header auth and never offers a sign-in.

Other clients. Anything that speaks Streamable HTTP MCP can connect using the same shape as Cursor's config. If your client only speaks stdio, bridge it with npx -y mcp-remote https://api.remoet.dev/mcp/oauth.

3. Ask the agent something

A short script you can paste straight in:

Search Remoet for senior backend roles that use Go, remote or hybrid, sorted by salary. Then find the companies behind the best three, check their stacks against my profile, and star the ones worth hearing from again.

That single prompt exercises five tools. If everything's wired up, you'll get a shortlist in under a minute.

What every account gets

I'm going to put the limits in plain numbers because vague copy helps nobody self-select.

• One star is enough. Star a single company and the delivery loop is already running. No five-star activation gate, no waiting room. The active-star cap is fifty, which is room for a real shortlist without pretending it's a bookmarking tool.

• 25 unstars per 30 days. Stars are a commitment. Unstarring costs budget so people don't churn through the catalogue. If you hit the unstar wall, that's the signal that you're starring too aggressively.

• 5,000 MCP requests per day. A "request" is one tool call. The example prompt above costs about five. Most daily-driver sessions land between five and twenty, so this is an abuse backstop rather than something you'll feel.

• 5,000 API requests per day. Separate quota for direct API users (calling the GraphQL API yourself, not going through your agent).

• 10 link trees. Your dev-flavored profile pages.

• Job data is live. No delay, no waiting room.

Those are the limits for everyone. There is nothing to upgrade to.

Why a quiet start

I wanted to find the rough edges with real agents before opening the floodgates. A staging instance, no matter how thoroughly it's tested, doesn't surface the weird stuff. The 4am tool call that fails on a session edge case. The prompt phrasing the model picks that exposes a tool description ambiguity. The limit that turns out to be too tight or too loose for the actual workflow.

So: a quiet start, and a handful of corrections along the way based on what early users told me.

What I want from you

If you connect, the most useful thing you can do is tell me what broke or what felt clunky. Reply to the email, ping me on Discord, open a GitHub issue on the docs repo. I read all of it personally. The agent-era job platform is not a thing you build in a vacuum. It's a thing you build in a feedback loop with the people using it.

If it works smoothly, I want to hear that too. Send me your prompt, the time it took, the shortlist it gave you. Those are the stories that go into the next round of marketing, and they always read better than anything I'd write.

The full /mcp page is at remoet.dev/mcp with example prompts, the install snippets, and the FAQ. The agent job-search workflow guide is the deep walk-through of the daily loop.

Plug in. Tell me what breaks.

Happy hunting.