Jobseek

Name: Jobseek
Author: colophon-group

作者：colophon-group版本 0.2.0i★ 224i在你的电脑上运行

注册名称io.github.colophon-group/jobseek

安装

概览

作者提供的说明（英文原文）

Search jobs and companies on Job Seek (jseek.co)

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i2 项中通过 2 项依据公开信息检查；尚未扫描代码
使用情况i正在增长↓ 70/周 · ★ 224

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 搜索与 AI 记忆

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：2 项中通过 2 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
注册中心没有列出需要填写的密钥。

你需要

npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "jobseek": {
      "command": "npx",
      "args": [
        "-y",
        "@jseek/mcp-server"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add jobseek -- npx -y @jseek/mcp-server

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "jobseek": {
      "command": "npx",
      "args": [
        "-y",
        "@jseek/mcp-server"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "jobseek": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@jseek/mcp-server"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月10日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 colophon-group 验证，该账户拥有此仓库
✓ 通过
仍在维护
代码最后更新于昨天
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

星标数多于此分类中其他 5866 个服务器的 98%
发布到注册中心的时间比此分类中其他 5866 个服务器的 35% 更新
基础检查结果等于或优于此分类中其他 5866 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Jobseek 安全吗？

它在 2 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于昨天，最新版本（0.2.0）于2个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它？

同一分类中有：Ruflo, Context7, Metabase

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：↓ 每周下载量i★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Ruflo

Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.

作者：ruvnet广泛使用↓ 7.4万/周★ 8.1万今天更新

在你的电脑上运行

安装

Context7

Up-to-date docs for AI agents

作者：upstash广泛使用↓ 125万/周★ 6.4万昨天更新

电脑或云端

安装

Metabase

Lets AI clients search, explore, query, and visualize data in a Metabase instance.

作者：metabase广泛使用★ 5万6个月前更新

在云端运行

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Job Seek

Follow companies you care about. Find the right jobs. Keep your applications moving.

Job Seek brings jobs from thousands of company career pages into one search. Build watchlists, get weekly email job alerts, and track applications in one place. Free to start, with English, German, French, and Italian interfaces.

Try jseek.co → · See the features · Use the MCP server · Add a company · Run it yourself

Tracking Stripe · Anthropic · OpenAI · Figma · Vercel · Datadog · Mistral · Hugging Face · Linear · Notion · Roche · Nestlé · UBS · Swisscom · ABB · SAP · Siemens · Klarna · N26 · Wise · Monzo — and thousands more. Browse the source-of-truth registry in companies.csv.

Why Job Seek

Your next role might be at a company you already admire—or one you haven’t discovered yet. Search across employer career sites, follow a shortlist of companies, and spend less time checking the same pages for updates.

Jobs from the source. Browse employer career pages and ATS feeds. Every listing links back to the original posting.
Filters that travel with you. Combine role, seniority, location, technology, work mode, salary, experience, and posting language, then save your search as a watchlist.
A free job-search workspace. Up to 10 watchlists, weekly email digests, and an application tracker for jobs saved on Job Seek.
A closer fit with Pro. Narrowed reads job descriptions against your personal criteria, beyond job titles and standard filters.
Open-source and accessible from your tools. Use the web app, public REST API, or hosted MCP server.

What you get on jseek.co

Search jobs across company career pages

Explore without an account. Combine filters to find relevant openings across thousands of employers, from engineering and design to finance, operations, healthcare, and more.

Follow companies and get weekly job alerts

Save a watchlist for each direction you’re considering: selected employers, a role, a location, or a combination. Enable notifications to receive a weekly email digest of new matches. Share a watchlist by link with someone else looking for similar work.

Track applications, interviews, and offers

Save a job, record when you apply, add interview rounds and dates, and update the outcome. Your application tracker keeps the original job details alongside your progress; pipeline statistics help you see how the search is going.

Find the work behind the job title with Narrowed

Two roles can have the same title and very different responsibilities. Describe what matters to you in plain language:

I want to work directly with users and turn their problems into product improvements. No people management.

Narrowed checks the descriptions in your watchlist and picks out the matches. It is included with Job Seek Pro; regular search, watchlists, weekly email digests, and application tracking remain free. See Pro details and current availability.

Get to know an employer’s hiring

Company pages bring together current openings, posting activity, and similar employers. Open a role at its source or use what you find to build your next watchlist.

Start your job search →

Built by Colophon Group, a small team in Switzerland. Available in English, Deutsch, français, and italiano.

Use Job Seek from AI tools and code

The hosted MCP endpoint exposes tools for job search, posting metadata, company lookup, filter discovery, and prefilled watchlist links. It also accepts bug reports, feature suggestions, and usability feedback through three write tools:

https://jseek.co/mcp

It uses Streamable HTTP and does not require authentication. Add the URL as a custom MCP connector, or run the published package locally:

npx @jseek/mcp-server

See packages/mcp-server/README.md for client-specific setup and tool examples. For direct HTTP integrations, the public REST contract is available at /openapi.json.

Add a company

Open issues labelled company-request are companies waiting to be added. The production backlog is processed by an isolated, Hetzner-hosted Codex runner; contributors can resolve an issue with any capable coding agent that follows the repository instructions.

`ws` is an agent utility. It renders the workflow, manages isolated state, and enforces the validation gates; it is not intended as a hand-configured interactive wizard.

The environment needs git, an authenticated gh CLI, Python 3.13+, and web access. Install the workflow package:

pip install jobseek-crawler-setup

Then give your coding agent this task:

Run ws task --issue and follow the printed instructions.

ws fetches the issue, checks for duplicates, researches the company and all relevant career boards, guides monitor and scraper selection, validates extracted data and brand assets, and opens the pull request. The registered crawler types cover common ATS APIs, sitemaps, structured data, rendered pages, PDFs, and vendor-specific formats.

No issue for the company you want? Request it. Anyone can.

The maintained workflow reference is docs/01-agent-workflow.md.

Architecture

Company and board CSVs are the configuration source of truth. The crawler keeps operational state in its own Postgres database, uses Redis for scheduling, publishes searchable documents to Typesense, and stores full descriptions in S3-compatible object storage. The web app owns authentication, watchlists, and application-tracker data in a separate Postgres boundary.

%%{init: {"flowchart": {"rankSpacing": 24}}}%%

flowchart TD Requests["Company requests"] --> Agent["Coding-agent PR"] Agent --> CSV["companies.csv + boards.csv"] CSV --> Runtime["Crawler runtime sync · Redis · HTTP/browser workers · crawler Postgres"] Runtime --> ReadLayer["Published read layer Typesense · S3-compatible descriptions"] ReadLayer --> Web["Next.js web app · REST API · MCP"] Web <--> WebDB["Web Postgres"]

Start with the maintained documentation index, then read the system overview, crawler architecture, and Typesense reference.

Run it yourself

Job Seek is self-hostable, but the repository currently expects operator-managed services. The root docker-compose.yml is development scaffolding for Postgres and Typesense, not a complete one-command production deployment.

Prerequisites

Python 3.13+ and uv
Node.js 22+ and pnpm 10
A crawler-owned Postgres database
A separate web-owned Postgres database; both databases may run on the same server
Redis
Typesense
S3-compatible object storage for job descriptions

The important environment boundaries are:

Component	Core settings
Crawler database	`LOCAL_DATABASE_URL`
Web database	`WEB_DATABASE_URL` for crawler-side reads; `DATABASE_URL` for the web app
Redis	`REDIS_URL`
Typesense writes	`TYPESENSE_HOST`, `TYPESENSE_PORT`, `TYPESENSE_PROTOCOL`, `TYPESENSE_OPERATIONS_KEY`
Typesense web access	`TYPESENSE_SEARCH_KEY`, `TYPESENSE_WRITE_KEY`, and optionally `TYPESENSE_BROWSER_PARENT_KEY`
Description storage	`R2_ENDPOINT_URL`, `R2_ACCESS_KEY_ID`, `R2_SECRET_ACCESS_KEY`, `R2_BUCKET`, `R2_DOMAIN_URL`
Web authentication	`BETTER_AUTH_SECRET`, `BETTER_AUTH_URL`; OAuth and email providers are optional

After provisioning those services, create apps/crawler/.env.local (using its .env.example as a starting point) and apps/web/.env.local, then initialize in this order:

git clone https://github.com/colophon-group/jobseek

cd jobseek corepack enable pnpm install

Web-owned database

cd apps/web pnpm db:migrate

Crawler-owned database and derived stores

cd ../crawler uv sync uv run playwright install chromium-headless-shell # required by run-browser uv run alembic -c src/migrations/alembic.ini upgrade head uv run crawler setup-typesense uv run crawler sync

A complete crawler deployment keeps four process roles running:

uv run crawler run          # HTTP workers

uv run crawler run-browser # Playwright workers uv run crawler export # Postgres → Typesense CDC uv run crawler drain # descriptions → object storage

Start the frontend separately from apps/web:

pnpm dev                    # http://localhost:3000

Production operators should use scoped Typesense keys and read the deployment and recovery runbooks linked from docs/README.md.

What's in the repo

apps/crawler/              Python ingestion, normalization, scheduling, and export

src/core/monitors/ Career-board discovery: ATS APIs, sitemaps, DOM, feeds src/core/scrapers/ Posting extraction: JSON-LD, DOM, PDF, vendor formats src/workers/ HTTP workers, browser workers, and description drain src/exporter.py CDC from crawler Postgres to Typesense src/labeller/ Daily gold-dataset labelling and Hugging Face upload src/workspace/ ws workflow and Codex company-request runner data/companies.csv Company configuration source of truth data/boards.csv Career boards with monitor + scraper configuration

apps/web/ Next.js 16, Drizzle, Lingui, and Better Auth app/[lang]/ Localized product routes: en / de / fr / it app/api/v1/ Public REST API app/mcp/ Hosted Streamable HTTP MCP endpoint src/db/schem

只显示了开头部分；其余内容请在仓库中阅读