Sandbox
@amikai/openings-mcp

MCP server for job board and career site search

openings-mcp lets your agent search job listings across public job boards and company career sites through MCP. It supports many ATS backends and dedicated company careers pages, so you can ask one tool to look across a broad set of sources.

92 stars9 forksGoUpdated 23d ago
Who it's for

Builders who want their agent to search job listings across many boards and company career sites.

What it delivers

You can search jobs from your agent without visiting each site yourself.

What it does

Search many job sources

Queries job boards like 104, Cake, Jobindex, LinkedIn, and Indeed, plus dedicated company careers sites.

Supports many ATS platforms

Works with Workday, Ashby, Greenhouse, Lever, Teamtailor, Recruitee, Eightfold, SuccessFactors, SmartRecruiters, Workable, Rippling, iCIMS, Oracle Recruiting Cloud, JOIN, UKG Pro, Dayforce, Avature, H

Plugs into common MCP clients

The README shows setup for Claude Code, Codex, and Gemini CLI, with Docker as another option.

Company verification command

Includes `cmd/verify-companies` for checking and expanding the built-in company roster.

How to get it

  1. 1With Homebrew
    brew install --cask amikai/tap/openings-mcp
  2. 2With Go
    go install github.com/amikai/openings-mcp/cmd/openings-mcp@latest
  3. 3With Docker (multi-arch: linux/amd64, linux/arm64)
    docker pull ghcr.io/amikai/openings-mcp

README

openings-mcp

One MCP server to search job boards and company career sites.

openings-mcp searches job listings across job boards and company career sites from any MCP client: Claude Code, Codex, Gemini CLI, and others.

⚠️ Token use adds up fast when your client explores multiple postings or fetches full job details, so consider a cheaper model.

Demo of openings-mcp searching job listings from Claude Code

Disclaimer: This is an unofficial, personal-use tool. It is not affiliated with, endorsed by, or sponsored by 104 Corporation, TSMC, or any other job board or company whose listings it searches. It calls each site's public web endpoints; please respect their terms of service and use it at a reasonable, low frequency. The project ships no scraped job data.

Install

With Homebrew:

brew install --cask amikai/tap/openings-mcp

With Go:

go install github.com/amikai/openings-mcp/cmd/openings-mcp@latest

Upgrade by rerunning the same command; pin a version with @vX.Y.Z.

Without Go: download the archive for your platform from Releases and put openings-mcp on your PATH.

With Docker (multi-arch: linux/amd64, linux/arm64):

docker pull ghcr.io/amikai/openings-mcp

Add the MCP server to your tool

With openings-mcp on your PATH:

Claude Code

claude mcp add --scope user openings-mcp -- openings-mcp

Codex

codex mcp add openings-mcp -- openings-mcp

Gemini CLI

gemini mcp add openings-mcp openings-mcp

With Docker instead, replace openings-mcp with docker run -i --rm ghcr.io/amikai/openings-mcp, e.g.:

claude mcp add --scope user openings-mcp -- docker run -i --rm ghcr.io/amikai/openings-mcp

Disclaimer

This is an unofficial tool. It is not affiliated with, endorsed by, or supported by 104 Corporation, TSMC, or any other job board or company whose listings it searches.

Some providers rely on undocumented APIs that may change or stop working at any time without notice. Job listing data belongs to the respective sites. The server fetches it on your behalf when you invoke a tool and stores or redistributes nothing.

Use this tool for personal job searching at a human pace. Every request goes out from your own machine, and a site may throttle or temporarily block your IP if too many arrive too quickly. The server does not rate-limit requests, so a client that pages through many results or fetches lots of job details in one go can trip these limits. The server never logs in, so your accounts on these sites are not at risk. You are responsible for complying with the terms of service of each site you query; do not use it for bulk scraping or data harvesting.

Credits

Inspired by these MCP job-search servers:

Company roster data cross-referenced from:

  • OpenPostings — company/ATS discovery data used to expand the curated roster

Jobindex search reference:

License

MIT

Files in the repo

Repository payload19 top-level entries
  • .agents
  • .claude
  • .github
  • assets
  • cmd
  • docs
  • internal
  • unverified
  • .gitattributes
  • .gitignore
  • .goreleaser.yaml
  • AGENTS.md
  • CLAUDE.md
  • Dockerfile
  • go.mod
  • go.sum
  • LICENSE
  • Makefile
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k

x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

1.9k