GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者提供的说明(英文原文)
Dependency picker for coding agents: recommends, compares and scores GitHub repos with a verdict.
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。
GITHUB_TOKEN, WHICHLIB_TELEMETRY, X-GitHub-Token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": {
"whichlib": {
"command": "npx",
"args": [
"-y",
"whichlib"
],
"env": {
"GITHUB_TOKEN": "your-value",
"WHICHLIB_TELEMETRY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http whichlib https://whichlib.com/mcp --header 'X-GitHub-Token: your-value'claude mcp add whichlib --env GITHUB_TOKEN=your-value --env WHICHLIB_TELEMETRY=your-value -- npx -y whichlib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": {
"whichlib": {
"url": "https://whichlib.com/mcp",
"headers": {
"X-GitHub-Token": "your-value"
}
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"whichlib": {
"command": "npx",
"args": [
"-y",
"whichlib"
],
"env": {
"GITHUB_TOKEN": "your-value",
"WHICHLIB_TELEMETRY": "your-value"
}
}
}
}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": {
"whichlib": {
"type": "http",
"url": "https://whichlib.com/mcp",
"headers": {
"X-GitHub-Token": "your-value"
}
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"whichlib": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"whichlib"
],
"env": {
"GITHUB_TOKEN": "your-value",
"WHICHLIB_TELEMETRY": "your-value"
}
}
}
}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。
WHICHLIB_TELEMETRY envX-GitHub-Token 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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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6日
注册名称已通过 GitHub 账户 josifb 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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
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 1 项适用的基础检查中通过了 1 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:GITHUB_TOKEN, X-GitHub-Token
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(0.2.4)于9天前进入注册中心。
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:GitHub, Desktop Commander, Cloudflare MCP
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
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
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 dependency picker for coding agents. Ask which library to use and get a scored, verified answer instead of a guess.
whichlib is an MCP server with three tools. It speaks MCP 2026-07-28; older clients keep working. Every repository it returns carries a transparent 0–100 score (momentum, maintenance, adoption including npm and PyPI downloads, license), a tier, a one-line verdict and the full breakdown, so the agent can justify the pick and you can read why.
For teams (waitlist): alerts when a dependency your repos use goes stale, and rules your team's coding agents must follow when they add one. Add a 👍 to the waitlist issue; at 20 signups it gets built. whichlib itself stays free.
Claude Code:
claude mcp add whichlib -- npx -y whichlib
Cursor, Windsurf and other MCP clients:
{ "mcpServers": { "whichlib": { "command": "npx", "args": ["-y", "whichlib"] } } }
Requires Node 22 or newer. No account, no API key.
Use it without installing (hosted, no Node needed):
claude mcp add --transport http whichlib https://whichlib.com/mcp
Limits and the web API: https://whichlib.com/docs/
| Tool | Ask | You get |
|---|---|---|
recommend_repos | need in plain words, optional language, limit 1–10 | The best repositories for the need, ranked by fit (score × relevance), with downloads and a verdict each |
compare_repos | repos: 2–10 names as owner/repo | The repositories side by side, best first, same breakdown |
trending_repos | period day / week / month / rising, optional language, limit | Most-starred repositories created in the period, scored; rising: repositories of any age by stars gained this week |
Example, in Claude Code: "which Python PDF parser should I use?" → MinerU, pdfplumber, pypdf with scores, weekly downloads and verdicts like "Rising fast, 26k downloads/wk, pushed 3 days ago, Apache-2.0".
| Part | Weight | Signal |
|---|---|---|
| Momentum | 40% | Stars gained over 7 days (from daily star counts when available), else stars per day since creation, scaled by the npm/PyPI download trend when known (0.5–2x). Log scale. |
| Maintenance | 25% | Days since last push, full marks to 30 days, zero at a year. Widely used repos (10k+ stars or 100k+ weekly downloads) never drop below half. |
| Adoption | 25% | Stars, forks and npm / PyPI weekly downloads, log scale. |
| License | 10% | Permissive 1.0, weak copyleft 0.75, strong copyleft 0.5, none 0. |
Tiers: Strong ≥ 75, Solid ≥ 50, Watch ≥ 25, Avoid; repos younger than 30 days are New ("Too new to judge"), whatever their score. Archived repos are capped at 20. On a 20-need eval the top recommendation is an accepted answer 75% of the time and the top five contain one 100% of the time; the eval and its reports live in the repository.
GITHUB_TOKEN: raises GitHub's search limit from 10 to 30 per minute. A fine-grained token with no permissions is enough. Recommend makes three searches per call.WHICHLIB_HISTORY=off: do not download daily star counts. By default the server keeps the last 10 days in ~/.whichlib/stars/, refreshed in the background at most every 12 hours from raw.githubusercontent.com, so momentum uses real stars gained per week for the top 1,000 repos per language and new trending repos. Nothing is sent with that download.FRESH_REPOS_DATA_DIR: a folder of daily snapshots or star counts to use instead (see the repository's data branch).WHICHLIB_TELEMETRY=off or DO_NOT_TRACK=1: disables anonymous call counting. What is counted: tool name, a random install id, version, platform, Node major version, the MCP protocol version of the call. Never queries, repository names or results. The aggregate numbers are public at https://whichlib-telemetry.todorovskijosif.workers.dev/stats.Repository: https://github.com/josifb/whichlib (MIT). It also holds the Fresh Repos dashboard (most-starred new repositories, day / week / month, sortable, one HTML file), the nightly snapshot and enrichment jobs, the recommendation eval, and 80+ unit tests.
Development, from the whichlib/ folder of the repository:
npm test # unit tests, no network
npm run mcp:smoke # start the server over stdio and call every tool live npm run eval # 20-need recommendation eval (set GITHUB_TOKEN) npm run snapshot # today's top repos per period and language -> data/snapshots/ npm run enrich # add npm / PyPI packages and weekly downloads to the latest snapshot npm run score # top repos from the latest snapshot with score and verdict npm run pull-data # copy snapshots from the data branch
Layout:
mcp/server.mjs MCP entry (stdio) mcp/tools.mjs tool logic
mcp/expand.mjs query expansion mcp/telemetry.mjs anonymous call counting mcp/github-api.mjs GitHub client + cache mcp/data.mjs snapshot history provider mcp/eval/ needs, metrics, runner, inspect, results/ lib/score.js the score, shared by browser and Node snapshot/src/ query, normalize, github, registry, enrich, history, run, score-report, pull-data dashboard/index.html redirect to whichlib.com/repos (Fresh Repos)