remoet-labs/remoet-mcp
FreeNot checkedJob search for AI agents. Search tech companies by their real tech stack, star the ones that fit, and pull jobs from your shortlist. Profile, applications, and
About
Job search for AI agents. Search tech companies by their real tech stack, star the ones that fit, and pull jobs from your shortlist. Profile, applications, and digests over MCP. Free tier.
README
Connect your AI agent to Remoet, the job platform built for agents. Search tech companies by their real tech stack, star the ones you'd actually work for, pull jobs from that shortlist, and manage your developer profile, all through conversation.
This repo ships a local stdio MCP server (Node + TypeScript) plus the metadata MCP clients and directory registries need. The local server advertises Remoet's full tool catalog (snapshotted from the live server) and forwards calls to the hosted MCP at https://api.remoet.dev/mcp with your Bearer key. The hosted server is closed source and remains the source of truth for execution.
Most users connect to the hosted server directly (see Quick install below). The local package is for clients that prefer stdio or build/scan systems that require a runnable local server.
- Homepage: https://remoet.dev
- Docs: https://docs.remoet.dev
- MCP endpoint:
https://api.remoet.dev/mcp - Get a free API key: https://remoet.dev/onboarding
What it does
Remoet has company-level tech stack data nobody else has, so an agent can match you to companies by the technologies they actually use, not recruiter keyword tags. Star the companies that fit, and your agent pulls fresh jobs from that shortlist. It also manages your profile, applications, saved jobs, and weekly digests, all over MCP.
Free tier is the whole product with caps. Paid tiers unlock real-time job data and higher limits. No credit card for the free tier.
See tools.md for the full tool catalog.
Works with
Claude Code, Claude Desktop, Claude Web, Cursor, VS Code, Windsurf, Codex, and any MCP-compatible client. Also installable as an agentskills.io skill on OpenClaw (via ClawHub) and Hermes Agent. See Quick install.
Auth
Two transports, same tools:
https://api.remoet.dev/mcpexpects an API key as a Bearer header (Authorization: Bearer <key>). Best for CLI and always-on agents.https://api.remoet.dev/mcp/oauthruns OAuth 2.1 with PKCE and dynamic client registration. Best for browser clients like Claude Web and Desktop custom connectors.
Generate a key at remoet.dev/onboarding. The same key works for MCP and the REST API.
Quick install
Claude Code
claude mcp add --transport http --scope user remoet https://api.remoet.dev/mcp --header "Authorization: Bearer YOUR_KEY"
Then restart Claude Code (exit and relaunch) so the new server's tools load in a fresh session.
Cursor, VS Code, Windsurf
Add to your client's MCP config (the JSON in .mcp.json works as a template):
{
"mcpServers": {
"remoet": {
"type": "http",
"url": "https://api.remoet.dev/mcp",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}
Claude Web / Desktop (custom connector)
Add a custom connector pointing at https://api.remoet.dev/mcp/oauth and complete the browser sign-in. No API key to paste.
Remoet also ships as an agentskills.io skill, with one-command installs on Hermes and OpenClaw.
Hermes
hermes skills tap add remoet-labs/agent-skills
hermes skills install remoet-labs/agent-skills/skills/remoet
OpenClaw
openclaw skills install remoet
First prompt to try
I work in Rails, React, and Postgres. Which companies on Remoet hire for that stack?
Run locally (Node + Docker)
If you prefer a local stdio MCP server (or a build/scan system needs one), the same package is runnable directly.
With Node:
npm install
npm run build
REMOET_API_KEY="<your-key>" node dist/index.js
The server speaks MCP over stdio. Set REMOET_API_KEY to a free-tier key from remoet.dev/onboarding. Optionally override the upstream endpoint with REMOET_MCP_URL (defaults to https://api.remoet.dev/mcp).
With Docker:
docker build -t remoet-mcp .
docker run --rm -i -e REMOET_API_KEY="<your-key>" remoet-mcp
The container's entrypoint runs the stdio server. Pipe MCP JSON-RPC frames into the container; tool calls are forwarded to the hosted server with your Bearer key.
The published tool catalog lives in data/tools.json (snapshotted from the live tools/list). Refresh it whenever the hosted server's tool surface changes.
License
MIT. The wrapper is open; the Remoet backend it points at is a hosted service.
Install remoet-labs/remoet-mcp in Claude Desktop, Claude Code & Cursor
unyly install remoet-labs-remoet-mcpInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add remoet-labs-remoet-mcp -- npx -y github:remoet-labs/remoet-mcpFAQ
Is remoet-labs/remoet-mcp MCP free?
Yes, remoet-labs/remoet-mcp MCP is free — one-click install via Unyly at no cost.
Does remoet-labs/remoet-mcp need an API key?
No, remoet-labs/remoet-mcp runs without API keys or environment variables.
Is remoet-labs/remoet-mcp hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install remoet-labs/remoet-mcp in Claude Desktop, Claude Code or Cursor?
Open remoet-labs/remoet-mcp on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzCompare remoet-labs/remoet-mcp with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
