timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Checks whether an OpenAI-compatible endpoint publishes model prices without an account or key.
Skills that teach the AI this kind of work; they work alongside this one
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
Lists are ordered by a usage score (out of 100) built from these parts
| Popularity | 0/80 | GitHub stars or weekly downloads: the larger counts 60, the smaller 20 |
|---|---|---|
| Freshness | 12/12 | Full marks for a release or code change within 30 days |
| Still answering | 0/8 | The cloud endpoint answered at the last check |
| Usage score | 12/100 |
Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)
Pick the AI app you use, then copy the settings.
Passed 3/3 checks · Runs on your computer
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude, with some setup first
No key, nothing to install · Only the Claude desktop app (Windows or Mac), not the web or phone
Download the maker’s .mcpb file
The .mcpb file comes straight from the maker; we do not change it
Use Gateway Price Disclosure Check and tell me what you can do for me, then show me one thing✓ If Claude says it is using Gateway Price Disclosure Check or shows a Gateway Price Disclosure Check tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
ChatGPT cannot connect Gateway Price Disclosure Check yet
Gateway Price Disclosure Check runs on your computer, but ChatGPT can only connect servers that run on the web
A · Use an app that can connect Gateway Price Disclosure Check
Claude Code cannot connect Gateway Price Disclosure Check yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect Gateway Price Disclosure Check
Cursor cannot connect Gateway Price Disclosure Check yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect Gateway Price Disclosure Check
VS Code cannot connect Gateway Price Disclosure Check yet
The maker only provides an installer for the Claude desktop app
A · Use an app that can connect Gateway Price Disclosure Check
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Run on your computer in
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026
The registry name was verified with the GitHub account happy520ai, which owns the repo
Code last changed yesterday
Uses MIT
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Not checked: only npm and PyPI packages with a version can be checked
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/servers/happy520ai-gateway-price-check)Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed yesterday, and the latest version (0.5.8) reached the registry 33 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
Same category, other makers, commands already checked. Official ones first, then by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
Search and read Empryo's documentation. Read-only, no auth, no local access.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| This one Gateway Price Disclosure Check | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| Runs where | Installs on your computer | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install | Runs in the cloud, nothing to install |
| Needs a key | No | No | No | No | No | No |
| Add with + in Claude | No | Yes | Yes | Yes | No | No |
| Basic checks | 3/3 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| License | MIT | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| Price | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry | No cost listed in the registry |
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
一个只读问题:一个 OpenAI 兼容端点,在你没注册、没 key 的时候,愿不愿意把价格告诉你?
很多模型网关要先把账号建完、充完值,你才知道自己按什么单价付费。这个工具对任意端点发一次无鉴权 GET, 然后报告它公开返回了什么:有没有价格、有没有币种字段、有没有缓存价、有没有告诉你每个模型 id 背后是哪份权重。
# 不用 clone、不用装:一条命令直接跑(已实测,输出如上)
npx github:happy520ai/gateway-price-check
npx github:happy520ai/gateway-price-check --url https://your-gateway.example/v1 --name mine
node src/cli.mjs node src/cli.mjs --url https://your-gateway.example/v1 --name mine
单文件版(不用 clone、不用装依赖)放在 gist 里,由本仓库源码机械拼接生成,文件头写明生成自哪个 commit: gist.github.com/happy520ai/5f5f2a95385ef185f51a42c04a99cc46 — 重新生成 node make-gist-bundle.mjs,查是否过期 node make-gist-bundle.mjs --check。
下表与上面这张图都由 CI 从 results/latest.json 重写( 之间是机器区,手改会在下一次 每日跑批时被覆盖——覆盖不是 bug,是因为手抄的数字会在端点变动当天变成假话,而这张页面上的数字是给别人引用的)。 最新一次读数见 RESULTS.md。
| 判词 | 家数 | 是谁 |
|---|---|---|
YES 免登录就公布价格 | 3 | OpenCSG 19/21 · OpenRouter 478/478 · Vercel AI Gateway 501/516 |
NO 清单公开但一个价都不标 | 1 | NVIDIA NIM 0/32 |
AUTH 不注册连清单都看不到(401) | 7 | OpenAI · DeepSeek · SiliconFlow 硅基流动 · Alibaba DashScope 百炼 · Volcengine Ark 火山方舟 · Zhipu 智谱 · MiniMax |
三条读数:
currency 字段并按「元/百万 token」报。 这是单位可读性差异,不是透明度差异——透明度上 OpenRouter 是 478/478,比它更高。results/latest.json 每天被覆盖,所以不要引用它来支撑一个带日期的说法——你点进去的时候它已经是别的日子了。 带日期的读数在 results/history/,一天一个文件,CI 每天追加, 文件名与内容里的 as_of 由测试互锁(对不上就红),也不允许往回覆盖。
引用格式建议:gateway-price-check, reading of (UTC+08:00), results/history/ .json。
awesome-ai-gateway 的 canary-diff 方法。("五档"指判词 YES/NO/AUTH/ERR/UNKNOWN;"三档"指进程退出码 0/1/2。两个数不同源,别把它们当成同一个东西——本仓库的描述一度只写"three-tier verdicts",那是把退出码误当判词数。)
| 退出码 | 档位 | 含义 |
|---|---|---|
| 0 | YES / NO / AUTH | 清单读到了;或明确被鉴权挡住(401/403)——对"免登录可见价格"这个问题,AUTH 就是"否" |
| 1 | ERR | 端点不可达 / 非 401·403 的错误 / 不是 data[] 清单形状 / 清单为空 |
| 2 | UNKNOWN | 有条目带 pricing 对象,但一条都没有字段名落在识别词表内 |
ERR 与 NO 必须分开:一个返回空数组的端点,和一个明确列出 20 个模型却一个价都不标的端点, 是两件完全不同的事。AUTH 也不算 ERR——把 401 归成"探针失灵"会系统性高估整个行业的透明度, 这正是我第一版犯的错,是拿 OpenAI 和 DeepSeek 真跑了一遍才暴露的。 UNKNOWN 存在的原因是——如果服务商把价格放在 in_unit 这种我们没见过的键里, 一个只会数 prompt/price 的探针会报"0 条带价",那是探针瞎了,不是服务商不透明。 部分不认识时判 YES 并在判词里报出未解析条数与键名(Vercel 那 60 条就是这么露出来的)。
也在官方 MCP Registry 里:io.github.happy520ai/gateway-price-check(包是 .mcpb,stdio / node 运行时)。 在支持注册表的客户端里可以直接搜这个名字;核对用权威路由:
curl -s https://registry.modelcontextprotocol.io/v0/servers/io.github.happy520ai%2Fgateway-price-check/versions
(命名空间里有斜杠,必须编码成 %2F;?search= 那个面是缓存——0.5.6/0.5.7 发布后十几分钟,它仍返回 0.5.4。)
同一个测量,另一个入口。宿主是语言模型时,"能不能看价格"这个问题就变成它可以自己回答的事:
{
"mcpServers": { "gateway-price-check": { "command": "npx", "args": ["-y", "--package", "github:happy520ai/gateway-price-check", "gateway-price-check-mcp"] } } }
两把工具:
check_price_disclosure(url, name?) → 一次无鉴权 GET /v1/models,返回 YES/NO/AUTH/ERR/UNKNOWN + 条目数/带价数。内部就是 fork 一份 `src/cli.mjs`,所以 MCP 读数、CLI 读数、CI 归档读数出自同一条代码路径——两台仪器只有共享同一份声明时才算互证,共享同一段实现时才算不打架。latest_archive_readings(date?) → 读仓库里已归档的每日横评(默认今天,可给 YYYY-MM-DD)。三条设计约束,都是这个入口特有的:
GPC_ALLOW_INSECURE=1。initialize 的 instructions 里就把这句写死,免得模型转述成"它不透明"。-32601、未知工具/坏参数 -32602、被拒绝的 URL -32600;真跑但读不出结果才走 isError。这样宿主能区分"你没资格问"和"这个问题现在没答案"。test/mcp.test.mjs 真起子进程做 stdio 握手(9 条离线臂 + 1 条联网臂,CI 两个 OS 都开 GPC_LIVE_TESTS=1)。其中"通知不许有回包"那条自带正对照:先证明抓得到没人等的回包,再断言通知没有——否则那是一条空断言。
不用装东西,也不用写脚本:把 uses 指到 release tag,一次无鉴权 GET 就进你的流水线。
- uses: happy520ai/gateway-price-check@v0.3.0
with: url: https://ai.space.opencsg.com/v1 # …/v1 或完整 …/v1/models 都行 name: OpenCSG fail-on: 'NO' # 只有"清单公开却零价格"默认让 CI 转红
fail-on 默认是 NO,而 `ERR`/`UNKNOWN` 默认不失败——那两档说的是探针自己(网络不通、价格键长在词表外),把它们当"服务商不透明"会系统性低估行业的透明度。想让它们也拦,就显式写 fail-on: 'NO,ERR,UNKNOWN'。写进 fail-on 的词不在这五档内,action 会拒绝执行且不留下半截 outputs。
能照抄的真跑例子(含一条"必须红"的臂,用来证明 fail-on 不是装饰): .github/workflows/action-smoke.yml。
node --test
10 条用例里包含四条必中靶:空清单必须落到 ERR(不许落 NO)、全未知字段必须落到 UNKNOWN、 401 必须落到 AUTH 而 404 仍须是 ERR(不许把两种失败混成一档)、部分未知时判 YES 但判词必须带出未解析条数。 没有这四条,上面的分档承诺只是文档里的一句话。
编辑 src/providers.json,或直接用 --url。若对方用了新字段名,把键加进 src/probe.mjs 顶部的 PRICE_KEY / CACHE_KEY / UPSTREAM_KEY 三个正则,并补一条用例。
本仓库作者维护一个 OpenCSG 价格实测页, 那个页面带个人邀请码,有人经它注册我会拿到平台奖励。本工具与那份利益关系保持隔离: 默认配置里两个服务商是并列摆放的,而上面那张表里 OpenRouter 的透明度读数比 OpenCSG 更高 (478/478 带价 vs 19/21)。如果这个工具只对某一家说好话,它就没有存在价值。
MIT。