Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Search Thousands of jobs, Thousands of companies. MCP for Claude, ChatGPT, Codex and Cursor.
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。
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。
选择你使用的 AI 应用,然后复制设置。
Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
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 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"trackly": {
"command": "npx",
"args": [
"-y",
"trackly-cli",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add --transport http trackly https://mcp.usetrackly.app/api/mcp --header 'Authorization: your-value'claude mcp add trackly -- npx -y trackly-cli mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"trackly": {
"url": "https://mcp.usetrackly.app/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"trackly": {
"command": "npx",
"args": [
"-y",
"trackly-cli",
"mcp"
]
}
}
}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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"trackly": {
"type": "http",
"url": "https://mcp.usetrackly.app/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"trackly": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"trackly-cli",
"mcp"
]
}
}
}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。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 HTTP header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。
服务器要求先登录,才会列出它的工具。
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7日
注册名称已通过 GitHub 账户 trackly-app 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 850 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
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。
它在 3 项适用的基础检查中通过了 3 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。
你需要填写:Authorization
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(0.25.0)于前天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ 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
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
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。
The only job tracking CLI built for AI agents.
Search 250K+ jobs across 5,400+ companies and 40+ ATS types. Track applications, get AI-powered recommendations, and manage your job search -- from the terminal or through Claude, ChatGPT, Cursor, and other MCP-compatible AI agents.
Use Trackly directly inside your AI — zero config:
https://mcp.usetrackly.app/api/mcp[Full setup guide with screenshots →](https://usetrackly.app/connector)
Works in: Claude co-work (web), Claude Desktop, ChatGPT Connectors, and any MCP client that supports remote/streamable-http connectors.
npm install -g trackly-cli # may need: sudo npm install -g trackly-cli
trackly login trackly jobs --function product
Prerequisites: Node.js 20.20+ or 22.22+ (LTS recommended). On macOS with the official
.pkginstaller, global npm installs may requiresudo.
5,400+ companies | 250K+ jobs | 40+ ATS types | CLI + MCP | 58 local + 55 hosted MCP tools
trackly jobs # List jobs
trackly jobs --remote # Filter remote jobs (sets usStates=REMOTE) trackly jobs --region us # Filter by region (us, non_us, all, or a region tag: europe, canada, remote, ...) trackly jobs --job-type internship # Filter by employment type (full_time, internship, all) trackly jobs --work-arrangement hybrid,remote # Filter by work arrangement independently trackly jobs --function product # Filter by function trackly jobs --sponsorship exclude_no # Visa sponsorship filter (all, exclude_no, only_yes) trackly jobs --company 243 # Filter by company ID trackly job 1234 # Get job details trackly jobs 1234 # Alias for job details trackly companies # List companies trackly companies search "fintech" # Semantic company search trackly search "fintech" # Alias for semantic company search trackly stats # Show metrics trackly status # Alias for stats trackly preferences # Show discovery preferences and experience limits trackly preferences experience product=2 strategy=5 # Replace role-specific limits trackly preferences experience clear # Turn role-specific experience filtering off trackly apply 1234 # Mark as applied trackly save 1234 # Save a job trackly dismiss 1234 # Dismiss a job trackly ask "PM jobs in SF" # Natural language search (20/day) trackly contacts "Stripe" # Search contacts at a company trackly brief 1234 # Get network brief for a job trackly referral start 1234 # Start a referral campaign trackly referral status 1234 # Check referral campaign status trackly company-brief 243 # Get company brief (--refresh to regenerate) trackly company-workspace 243 # Full company workspace view trackly request-company "eBay" # Request a company be added (--url, --notes optional) trackly api-key create # Generate API key trackly api-key list # List API keys trackly config # Show current CLI config trackly config --api-key trk_xxx # Save an API key for future commands trackly version # Show installed version trackly whoami # Show current user trackly logout # Clear credentials trackly agent setup --client both # Install Trackly Apply for Codex + Claude Code trackly agent doctor # Verify setup, profile, resume, and compatibility trackly agent diagnose-path /path/to/upload.pdf --errno ENOSPC --json # Diagnose one exact local path
Add --json to any command for JSON output. Use --api-key or --base-url as one-off global flags when needed.
trackly preferences --json returns only success, experienceFilterV2Available, and preferences. The availability flag controls whether this client may edit role-specific limits; it does not claim that feed or alert enforcement is active. Every update checks that flag and the latest preference revision before writing.
No install. In your AI tool, open Settings → Connectors → Add custom connector and enter:
https://mcp.usetrackly.app/api/mcp
Sign in with Google when prompted. Full visual guide →
Claude Code can use the same hosted server over OAuth:
claude mcp add --transport http trackly https://mcp.usetrackly.app/api/mcp
OAuth sign-in is the default for every client. An API key is optional and only needed for headless clients that cannot complete an interactive sign-in: send Authorization: Bearer trk_... with a key from Settings → API Keys.
Remote connections get 55 hosted tools. They share the search, company, status, and Apply tools with the local server and add trackly_chat; the 4 local-only tools listed below are not available remotely. Hosted setup and tool details are at usetrackly.app/connector.
For agent-assisted form filling on macOS, install the public skill and local MCP together:
trackly agent setup --client codex # or claude / both
trackly agent doctor
For an existing MCP configuration or a Cloud harness, use trackly agent setup --client both --skills-only. This installs the same checksummed skill for both native clients without invoking their MCP commands or changing authentication. CLI 0.20.1 carries universal skill 4.9.1; its policy revision is the same numeric version, superseding the personal revisions. The policy accepts a documented markHandoff() guarantee with awaited calls, exact current tab checks, and revalidation on later turns. These observations are never reported as returned persistence receipts. Browser capabilities and manual Submit remain separate requirements; installation does not make a Linux browser supported. The separately installed trackly:trackly-apply plugin is updated through its plugin manager; plugin 1.1.1 carries the same browser and profile lookup policies. This setup command does not patch plugin caches.
The skill uses the profile and default resume in your Trackly account, asks only missing questions, fills user-approved saved jobs, and always stops before Submit. “Fill the next N” continues through the original recent-first Check Later snapshot until N unauthenticated forms are durably ready for your manual review; authentication walls and exclusions are reported separately and do not consume the target. An explicit “inspect the next N records” request still uses one fixed immutable batch. Support is fetched from Trackly at the start of every run: Greenhouse is full, Ashby and Lever are best effort, and 27 additional named ATS/provider classes use constrained guided mode. Employer-hosted unknown forms run only when Trackly binds them to a verified company domain. LinkedIn-hosted forms and unverified origins remain manual-only; a separately stored external application URL is evaluated under its own ATS and origin policy.
Guided mode is deliberately fail-closed. The agent stops on credential entry, OTP/email verification, CAPTCHA/human verification, an unexpected employer or origin, a submit-only transition, or any field whose committed state cannot be observed. trackly agent doctor checks the local skill, MCP registration, protocol compatibility, declared browser/computer-use configuration, profile completeness, and default-resume metadata. Live semantic browser capability and the exact resume bytes are verified at the start of a real run.
claude mcp add --scope user trackly -- trackly mcp
Or equivalently:
claude mcp add-json --scope user trackly '{"command":"trackly","args":["mcp"]}'
Add to a project-scoped .mcp.json:
{
"mcpServers": { "trackly": { "command": "trackly", "args": ["mcp"] } } }
Add to .cursor/mcp.json or ~/.cursor/mcp.json (same schema works for Windsurf):
{
"mcpServers": { "trackly": { "command": "trackly", "args": ["mcp"] } } }
Then use natural language in any of these clients:
trackly_search_jobs supports multiple roles and regions, US states and Canadian provinces, internship education levels, favorite companies, posting windows, annual USD salary floors, incremental sync, work arrangement, sponsorship and pipeline status. Exact values and examples. Search returns 20 jobs by default; request up to 100 and use offset to page.
For sponsorship, “exclude no” keeps yes and not mentioned. Use exclude_no; only_yes excludes jobs with unknown sponsorship. Ask the user when intent is ambiguous. Salary floors also keep unknown and non-comparable salaries visible. Unsupported industry/specialization/literal-search controls are rejected.
For a local server without a global package install, run npx -y trackly-cli mcp. For Codex, use codex mcp add trackly -- npx -y trackly-cli mcp; Cursor and Windsurf can use "command": "npx", "args": ["-y", "trackly-cli", "mcp"]. Authenticate with npx -y trackly-cli login first, or configure TRACKLY_API_KEY.
Existing global installs require npm install --global trackly-cli@latest. Restart the MCP process/client and refresh tool discovery after updating. For native skills and marketplace plugin updates, follow the release and update guide. Hosted and local releases are separate: the current client schema is authoritative.
The local stdio server (trackly mcp) registers the 58 tools below. Four are local-only because they run their checks on your machine: trackly_diagnose_local_path, trackly_lint_application_text, trackly_validate_apply_resume_upload, and trackly_validate_apply_tab_keep_set. The hosted server omits those four and adds trackly_chat, for 55 hosted tools.
| Tool | Description |
|---|---|
| trackly_search_jobs | Search by roles, regions, states/provinces, internship level, favorites, recency, annual USD salary floor, sponsorship, work arrangement, and pipeline status |
| trackly_get_job | Get details by Trackly ID, with availability and retry guidance |
| trackly_search_companies | Semantic company search |
| trackly_list_companies | List all tracked companies |
| trackly_get_stats | Job tracker metrics and status counts |
| trackly_get_preferences | Read bounded discovery preferences, edit availability, and save revision |
| trackly_update_experience_limits | Atomically replace role-specific limits on a job's stated minimum years |
| trackly_update_status | Mark jobs as applied, saved, or dismi
只显示了开头部分;其余内容请在仓库中阅读