Stringers MCP server
Commit Nov 13, 2026Enables AI agents to research market trends, product growth, and competitor strategies using 15 real-time data libraries.
Also known as komako-workshop/stringers, stringers
- Stars
- 11
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.2.0
- Last commit
- Nov 13, 2026
- License
- MIT
What is Stringers MCP?
Stringers enables AI agents to research market trends, product growth, and competitor strategies using 15 real-time data libraries.
Summary generated from the project's README
About Stringers MCP server
Stringers provides AI agents with access to real-time market intelligence and product growth data. It connects to 15 distinct databases, including payment-verified indie revenue, App Store and Google Play charts, GitHub star history, and advertising libraries from Meta, Google, and TikTok. This allows developers and product researchers to use agents like Claude Code, Cursor, or Trae to investigate why specific small products are gaining traction and how they acquire users.
The server operates as a remote MCP server via Streamable HTTP using a unique token obtained through a Google login. It includes specialized tools such as feed for market dynamics, plays for distilled growth playbooks, hot for trending individual products, products for researching specific apps or websites, and data for direct database queries. During the beta period, users can perform up to 200 database queries per day, with X real-time searches limited to 50 per day.
What you can do with it
- 1Discover proven growth playbooksRequest step-by-step strategies and real-world examples of successful product launches to apply to your own projects.
Written from the project's README. Every use case is checked against a quote from it.
How to install Stringers MCP
Formats verified 10 Nov 2026Install Stringers MCP in Claude Code
$ claude mcp add --transport http stringers https://stringers.io/mcp/%7Btoken%7DInstall Stringers MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"stringers": {
"url": "https://stringers.io/mcp/%7Btoken%7D"
}
}
}Install Stringers MCP in VS Code
.vscode/mcp.json
{
"servers": {
"stringers": {
"type": "http",
"url": "https://stringers.io/mcp/%7Btoken%7D"
}
}
}Install Stringers MCP in Codex
~/.codex/config.toml
[mcp_servers.stringers] url = "https://stringers.io/mcp/%7Btoken%7D"
Install Stringers MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"stringers": {
"httpUrl": "https://stringers.io/mcp/%7Btoken%7D"
}
}
}Configuration
STRINGER_KEY
| Name | Description | |
|---|---|---|
| STRINGER_KEY | — |
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work
- Source repository linked and reachablekomako-workshop/stringers is public and reachablegithub.com/komako-workshop/stringers ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-11github.com/komako-workshop/stringers ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 518 msPass
README
View on GitHubstringer:把「什么值得做」接进你的 agent
什么值得做 每天回答一个问题:哪些小产品这几天突然涨起来了,为什么涨,你能照着学什么。
我们每天采集 15 个库:独立产品经支付平台校验的真实收入、App Store 115 个区和 Google Play 的榜单、Meta / Google / TikTok 广告库、GitHub、Product Hunt、Hacker News、X 上几个圈子……在这上面每天做三件事:
- 市场动态:从几千个候选里挑出数据上突然起来的小产品(App、开源项目、插件、网站、独立产品收入),逐条调查为什么是这几天涨、这波能不能持续,查完站不住的撤下。
- 打法:从这些调查里归纳出小团队能照着做的做法,每条有分步骤、真实案例和照做却没成的反例。
- 在涨的产品:三千多个逐个研究过的 App、GitHub 项目、Chrome 插件、网站,每个写了它靠什么拿到用户,给了跟进等级。
网页上是写好的调查。接进你自己的 agent(Claude Code、Cursor、Codex、Trae……)之后,它能读这些调查,也能直接去查背后的库,再结合你自己的情况回答。
这个仓库是接入用的那一层:说明、Claude Code 插件、skill、命令行。采集和服务端不在这里。
English: Stringers (「什么值得做」, stringers.io) tracks which small products suddenly took off each day and investigates why, one by one, using 15 databases collected daily (payment-verified indie revenue, App Store / Google Play charts, Meta / Google / TikTok ad libraries, GitHub, Product Hunt, Hacker News, X). This repo connects it to your agent: a remote MCP server (
https://stringers.io/mcp/{token}, toolsfeed/plays/hot/products/data), a Claude Code plugin, an Agent Skill and a CLI. English site: stringers.io/en/; sign in with Google to get a token.
30 秒接上
- 打开 stringers.io,登录(手机号 + 验证码,或 Google 账号;未注册的自动建号)。
- 点配置 agent,复制那段话,发给你的 agent。
- 它自己把配置加好。接通以后直接问。
不用往终端里贴命令。那段话里有你的专属地址,长这样:
https://stringers.io/mcp/wt_xxxxxxxxxxxxxxxxxxxxxxxx
这个地址就是你的 token,别发到公开的地方。泄露了在「配置 agent」里点「换一个新地址」,旧的立刻失效。
Claude Code 插件
已经有 token(登录后「配置 agent」里那个地址,/mcp/ 后面 wt_ 开头的一段),在 Claude Code 里:
/plugin marketplace add komako-workshop/stringers
/plugin install stringer@stringers
安装时会问 token。MCP 和 skill 一起装好。
手动配置
agent 改不了自己的配置,或者你想自己来,按客户端加一个远程 MCP 服务器:名字 stringer,类型 Streamable HTTP,地址填上面那个。
Claude Code
claude mcp add --transport http --scope user stringer https://stringers.io/mcp/<token>
Cursor:~/.cursor/mcp.json
{ "mcpServers": { "stringer": { "url": "https://stringers.io/mcp/<token>" } } }
Codex:~/.codex/config.toml
[mcp_servers.stringer]
url = "https://stringers.io/mcp/<token>"
Trae / Windsurf / Cherry Studio 等:设置里添加 MCP 服务器,类型选 Streamable HTTP(或「可流式传输的 HTTP」),填地址。只认 JSON 的,用上面 Cursor 那段。
只支持本地命令(stdio)的客户端:装下面的命令行,配置成运行 stringer mcp。
能问什么
- 今天有哪些小产品突然涨起来了?各自是为什么涨的?
- 最近靠投广告起量的 App 有哪些?它们的素材是怎么写的?
- 我做了一个开源工具,没人知道。有没有能照着做的起量打法?
- 最近 30 天收入涨得最快的 AI 视频类独立产品是哪几个?各自怎么获客的?
- 我想做一个给 Claude 用的 MCP 工具,现在谁在做、赚到钱了吗?
- 我一个人、会前端、每晚两小时,最近涨起来的东西里哪个我能跟?
工具
| 工具 | 做什么 |
|---|---|
feed |
市场动态:数据上突然涨起来的小产品,每条都逐个调查过为什么是这几天涨。不带参数给最新一天;day 看某一天;q 按短词在全部日期里搜;slug 读一条的完整调查(定位、对手、时间线、出处、哪些没查实) |
plays |
打法:从这些调查里归纳的做法,每条有分步骤、真实案例(带数字和日期)、照做却没成的反例、适合谁、什么时候不灵。不带参数给清单;id="p04" 读全文;q 搜 |
hot |
爆款单品:编辑每天从各库挑的、正在爆而且小团队有机会的单个产品,带数字(来源和日期)、为什么在爆、对你的机会;past=true 连已下榜的也给 |
products |
在涨的单个产品:移动端 App、GitHub 开源项目、Chrome 插件、网站,每个都研究过为什么跑出来、怎么跟,并给了等级;sec 选板块(apps / github / chrome / web),grade、q 筛,key 读整篇文章;growth="关键词" 按「怎么起量」搜案例,key 加 part="growth" 只读它怎么拿到用户(已经有产品、问怎么推广时用) |
data |
直接查一个原始库(只读):lib 是库名,args 是参数;第一次查某个库先 args="schema" |
产品的等级:现在跟进它是不是好机会,也就是一两个人、几个月做出来并赚到钱的概率。S 最值得跟,E 别碰。GitHub 项目按「能不能也拿到 star」判断,不谈钱。
以前的约 90 个「方向」长文和评级(工具
today/directions/direction)2026-11-12 起停止更新,工具已撤下。存档还在 stringers.io/all.html。
能查的库
| 库 | 内容 |
|---|---|
indie |
独立产品经支付平台校验的真实收入(约 1.2 万个产品,逐日 / 逐月) |
forsale |
在售的小生意(Acquire / Flippa):要价、年收入、利润,卖家自填 |
appstore |
App Store 115 个区的榜单、评分、评论、新上架(没有下载量和收入) |
googleplay |
Google Play 30 个区:榜单、精确安装量、评分 |
macappstore |
Mac App Store 20 个区的免费 / 付费榜 |
chromestore |
Chrome 商店扩展:用户数、评分、收费迹象 |
shopifyapps |
Shopify 应用商店:定价、评分、评论速度 |
github |
GitHub ≥50 星的库约 85 万个,每天的星数,trending |
producthunt |
Product Hunt 发布、票数、makers(2013 年起) |
hackernews |
Hacker News 故事与分数、Show HN(2024 年起) |
metaads |
Meta 广告库:谁在买量、在投多少条、落地到哪 |
googleads |
Google 广告透明中心:赢家名单上的产品在不在 Google 买量 |
tiktokads |
TikTok 广告库(只有投欧洲的) |
crossing |
过线名单:每天在 7 个库里算「今天刚冒头的」 |
x |
X 上五个圈子(AI 创始人 / 独立开发者 / 研究员 / 美股投资人 / VC)的原创帖,也能现查 X |
每个库点进去是一页说明:能问什么、一次真实查询今天返回了什么、这个库不能证明什么(全部 15 个库和 5 种用法)。各库的表、字段、口径和边界,让 agent 用 data 查 schema;数据到哪天看 stringers.io/status.html。
English
Stringers is an MCP server for product research: it gives your AI agent (Claude Code, Cursor, Codex…) read access to 15 databases we collect every day, plus our daily investigations into which small products suddenly took off and why, and the playbooks we distilled from them.
Ask your agent things like:
- Which small products took off this week, and what drove each one?
- Which indie video tools make more than $5,000 a month, and how do they get users?
- Which apps released in the last 60 days are gaining installs fastest?
- Where do my competitors advertise — Meta, Google or TikTok — and are they scaling up?
- I do front-end, solo, two hours a night. What should I build?
| Database | What it holds |
|---|---|
indie |
Payment-verified revenue for ~12,000 indie products, daily and monthly |
forsale |
Small online businesses listed on Acquire / Flippa: price, revenue, profit |
appstore |
App Store charts for 115 regions, ratings, reviews, new releases |
googleplay |
Google Play charts for 30 stores with exact install counts |
macappstore |
Mac App Store free / paid charts for 20 regions |
chromestore |
Chrome extensions: users, ratings, signs of monetisation |
shopifyapps |
Shopify apps: pricing, ratings, review velocity |
github |
Daily star history for ~850,000 repositories |
producthunt |
Product Hunt launches, votes and makers since 2013 |
hackernews |
Hacker News stories and Show HN since 2024 |
metaads |
Meta Ad Library: who is buying ads, how many, landing where |
googleads |
Google Ads Transparency Center for products on our watchlist |
tiktokads |
TikTok ad library (ads served in Europe only) |
crossing |
Daily breakout list computed across 7 databases |
x |
Posts from five X circles, plus live X search |
Each link shows example questions, a real query with today's output, and what the data cannot prove. Workflows: product research · validate an idea · competitor ads · rising apps · first users.
Setup is the same as above: a remote MCP server (Streamable HTTP) at https://stringers.io/mcp/<token>, tools feed (daily breakouts, each investigated) / plays (playbooks with steps, cases and counter-examples) / hot / products / data. Free during beta (200 queries a day). Tool output is in Chinese (your agent answers in your language); the site is in English under stringers.io/en/. Get your personal URL by signing in with Google at stringers.io/en/start.html.
限额
测试阶段免费。每个 token 每天查库 200 次,其中 X 实时查询 50 次;每次结果最多 50 行。feed / plays / hot / products 不算在查库次数里。
我们会记下你的 agent 查了什么,以及它转述的「你这次想弄清什么」(工具的可选参数 ask,一句话、不带个人信息),用来知道大家关心什么、该补哪些数据;手机号或 Google 账号只用来认出你。这些都不会公开。
命令行(可选)
一个 Python 文件,只用标准库。
curl -fsSL https://raw.githubusercontent.com/komako-workshop/stringers/main/cli/stringer -o ~/.local/bin/stringer && chmod +x ~/.local/bin/stringer
export STRINGER_KEY=wt_… # token(或写到 ~/.config/stringer/key;整条地址也行)
stringer feed # 市场动态,最新一天
stringer feed -q 广告 # 在全部日期里搜
stringer feed <slug> # 一条动态的完整调查
stringer plays # 打法清单
stringer plays p04 # 一条打法全文
stringer products --sec apps --grade AB # 在涨的产品
stringer libs # 能查的库
stringer schema indie # 先看口径和边界
stringer indie top --min 1000 # 参数就是各库命令的参数
stringer mcp # 以 stdio MCP 跑
除了 status 都要 token;没有 token 时 stringer feed 退回读首页的公开 Markdown 版。list / show <编号> 还能读已停更的方向存档。
skill(可选)
skills/stringer/SKILL.md 教 agent 怎么用这些调查:几种常见问法怎么答、等级怎么转述、什么时候去查库。接了 MCP 就够用;想让回答更稳,再装它:
- Claude Code:装上面的插件就带了;或者把
skills/stringer/拷到~/.claude/skills/stringer/ - Cursor:内容放进
.cursor/rules/stringer.mdc
没接 MCP 也能用一部分:skill 会让 agent 读首页的公开 Markdown 版(https://stringers.io/index.md,近几天的市场动态)和 /api/apps.json 这类公开 json,只是读不了每条的完整调查和打法,也查不了库。
反馈
数字不对、某条调查的原因找错了、想要哪个库、哪个客户端接不上:开 issue。
许可
本仓库代码 MIT。网站上的文章、判断和数据版权归「什么值得做」所有,引用请注明出处并附链接。
Stringers MCP questions
How do I add Stringers MCP to Claude Code?
Run claude mcp add --transport http stringers https://stringers.io/mcp/%7Btoken%7D in your terminal. Add --scope user to make it available in every project.
How do I add Stringers MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What can I ask the agent?
You can ask about products that suddenly took off, apps gaining installs via ads, successful growth playbooks, or specific revenue trends in categories like AI video.
Is there a limit to how much I can query?
During the beta period, it is free with a limit of 200 database queries per day per token, while X real-time searches are limited to 50 per day.
What kind of data sources are included?
The server accesses 15 databases including App Store/Google Play charts, GitHub stars, Product Hunt, Meta/Google/TikTok ad libraries, and verified indie revenue.
Does the server support different languages?
The tool output is provided in Chinese, but your AI agent will translate and answer in your preferred language.