MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
HubSpot CRM objects, properties, owners, and associations: list, search, write.
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": {
"crmport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/crmport",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add crmport -- npx -y @reneturcios/crmport mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"crmport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/crmport",
"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": {
"crmport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/crmport",
"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7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:MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
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
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
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。
crmport is a small workbench for a HubSpot CRM portal. It treats the CRM the way the API does: everything is an object — a contact, a company, a deal, a ticket — identified by an object type and an ID, carrying a free-form map of properties. From that one idea crmport lists objects with paging, searches them with HubSpot filter groups, reads, creates, updates, and archives them one at a time or in a batch, inspects the property definitions for a type, looks up the owners who can hold records, and reads or creates the associations that connect one object to another. One binary serves a command-line interface and a stdio MCP server.
A HubSpot private-app access token is required. Put it in the HUBSPOT_ACCESS_TOKEN environment variable; it is sent to the API as an Authorization: Bearer header and never appears in output. When the variable is missing, every call fails with an error that names it, before any request is made.
This is a core subset of the HubSpot platform: CRM objects, properties, owners, and associations. Files, forms, marketing email, blogs and CMS content, custom object schema creation, workflows, and OAuth app management are not part of this tool.
npx @reneturcios/crmport list contacts --limit 10
Or run the container image:
docker run -i -e HUBSPOT_ACCESS_TOKEN ghcr.io/cloudcorprecords/crmport
The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.
export HUBSPOT_ACCESS_TOKEN=<redacted>
crmport list contacts --limit 25 --properties firstname,email crmport search contacts '[{"filters":[{"propertyName":"lastname","operator":"EQ","value":"Smith"}]}]' crmport get contacts 12345 crmport create deals '{"dealname":"New deal","amount":"5000"}' crmport update deals 67890 '{"amount":"7500"}' crmport delete tickets 11111 crmport batch-create companies '[{"properties":{"name":"Acme"}}]' crmport properties contacts crmport owner 22222 crmport owners --limit 10 crmport associations contacts 12345 companies crmport associate contacts 12345 companies 99999 --type-id 1
crmport --version
Each command prints the upstream JSON payload. Exit codes: 0 on success, 1 when a call fails (including a missing HUBSPOT_ACCESS_TOKEN or an API error), 2 for usage errors.
One bin serves both faces. The mcp subcommand starts a stdio MCP server:
npx -y @reneturcios/crmport mcp
MCP client configuration:
{
"mcpServers": { "crmport": { "command": "npx", "args": ["-y", "@reneturcios/crmport", "mcp"], "env": { "HUBSPOT_ACCESS_TOKEN": "pat-..." } } } }
| Tool | Input | What it returns |
|---|---|---|
hubspot_list_objects | objectType (required), limit, after, properties (optional) | A page of CRM objects of that type. |
hubspot_search_objects | objectType, filterGroups (required), properties, limit, after, sorts (optional) | Objects matching the filter groups. |
hubspot_get_object | objectType, objectId (required), properties (optional) | The single object. |
hubspot_create_object | objectType, properties (required), associations (optional) | The created object. |
hubspot_update_object | objectType, objectId, properties (required) | The updated object. |
hubspot_delete_object | objectType, objectId (required) | An archive receipt; HubSpot's delete moves the object to the recycle bin. |
hubspot_batch_create_objects | objectType, inputs (required) | The batch creation results. |
hubspot_list_properties | objectType (required) | Property definitions for the type. |
hubspot_get_owner | ownerId (required) | The owner record. |
hubspot_list_owners | limit, after (optional) | A page of owners. |
hubspot_list_associations | objectType, objectId, toObjectType (required), limit, after (optional) | Associations from the object to the other type. |
hubspot_create_association | objectType, objectId, toObjectType, toObjectId (required), associationTypeId (optional) | The created association. |
Object reads and writes use the CRM v3 endpoints under https://api.hubapi.com/crm/v3/objects/{objectType}; properties live under /crm/v3/properties/{objectType} and owners under /crm/v3/owners. Associations use the v4 endpoints under /crm/v4/objects/{objectType}/{id}/associations/{toObjectType}.
npm install
npm run build # tsc -> dist/ npm test # node test runner over test/*.test.ts, no network (fake fetch fixtures) npm run dev # run the CLI from source via tsx
MIT — see LICENSE.