Agro API MCP by usefulapi
Read satellite, NDVI, weather and soil data; create and delete fields in Agro API.
作者提供的说明(英文原文)
Find the tests relevant to a source file from an import map, ranked, with the run command.
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。
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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"testfinder": {
"command": "npx",
"args": [
"-y",
"@reneturcios/testfinder",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add testfinder -- npx -y @reneturcios/testfinder mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"testfinder": {
"command": "npx",
"args": [
"-y",
"@reneturcios/testfinder",
"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": {
"testfinder": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/testfinder",
"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。
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8日
注册名称已通过 GitHub 账户 CloudCorpRecords 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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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。
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)。
GitHub 仓库最后更新于–,最新版本(0.1.0)于5天前进入注册中心。
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, Docker。
同一分类中有:Agro API MCP by usefulapi, FieldClimate MCP by usefulapi, Exely MCP by usefulapi
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
Read satellite, NDVI, weather and soil data; create and delete fields in Agro API.
Read weather station data, sensors, farms, fields and crop zones in FieldClimate.
Read hotel bookings, rooms, cancellation rules and daily occupancy in Exely.
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。
Running the whole test suite after every small edit is a slow loop. testfinder narrows it: give it one source file plus the project's file/import map — every file's path and the paths it imports — and it works out which tests are actually relevant to that file, why each one is relevant, and the exact command that runs just those tests:
.test or .spec inserted before the final extension, either beside the source (src/foo.ts → src/foo.test.ts) or in the __tests__ form (src/__tests__/foo.test.ts). A source whose name has no extension gets the suffix appended instead (src/foo → src/foo.test).Every relevant test carries exactly one reason, decided by precedence: self (the source file is itself a test) over direct over convention over transitive. Results are ranked by that reason order, then by distance, then by path, and run_command is the npx tsx --test line that runs them in ranked order — or null when nothing is relevant. The result also reports total_files and test_files_considered, the count of test files in the set whether relevant or not. A file counts as a test when its name carries .test. / .spec. (or ends in .test / .spec), or when it lives under a test, tests, or __tests__ directory.
Imports that name paths outside the supplied set are external: they are ignored, never followed, and never an error. Duplicate import entries are de-duplicated and a file importing itself is ignored for graph purposes, though distances still flow through ordinary non-test files on the way to a test. Malformed input — a missing or unknown source_file, an empty file set, a duplicate file path, a wrongly typed field — is a validation error naming the offending path (for example files[1].imports[0] must be a string), and no partial result is produced. The computation is pure and local, and the tool only finds tests: running them, with the command it returns, is left to your own environment.
npx @reneturcios/testfinder find --input args.json
npx @reneturcios/testfinder --version
args.json contains the full arguments object:
{
"source_file": "src/foo.ts", "files": [ { "path": "src/foo.ts" }, { "path": "src/bar.ts", "imports": ["src/foo.ts"] }, { "path": "src/foo.test.ts" }, { "path": "src/bar.test.ts", "imports": ["src/bar.ts", "react"] } ] }
imports defaults to [] per file; here react is external to the set and ignored. src/foo.test.ts is a naming-convention match with no import of its own, and src/bar.test.ts reaches the source through src/bar.ts at distance 2. The result is printed as JSON:
{
"source_file": "src/foo.ts", "relevant_tests": [ { "path": "src/foo.test.ts", "reason": "convention", "distance": null }, { "path": "src/bar.test.ts", "reason": "transitive", "distance": 2 } ], "total_files": 4, "test_files_considered": 2, "run_command": "npx tsx --test src/foo.test.ts src/bar.test.ts" }
Exit codes: 0 on success, 1 on a runtime error (including an unreadable or invalid input file, or invalid input), 2 on a usage error.
npx -y @reneturcios/testfinder mcp
MCP client config:
{
"mcpServers": { "testfinder": { "command": "npx", "args": ["-y", "@reneturcios/testfinder", "mcp"] } } }
find_relevant_tests — Find the tests relevant to one source file from a file/import map.source_file (string, required) — path of the source file; must be one of the supplied filesfiles (array, required, at least one) — files as {path, imports?} objects; path is unique across the set, and each imports entry either names another supplied file or anything else (external, ignored)Returns {source_file, relevant_tests, total_files, test_files_considered, run_command}, where each entry of relevant_tests is {path, reason, distance}.
docker run -i ghcr.io/cloudcorprecords/testfinder
docker run --rm -v "$PWD:/w" ghcr.io/cloudcorprecords/testfinder find --input /w/args.json
npm install
npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (pure local, no network) npm run dev # run the CLI from source
MIT — Copyright (c) 2026 Rene Turcios