MCP YouTube Transcript
作者：jkawamoto
An MCP server retrieving transcripts of YouTube videos
在你的电脑上运行★ 495MIT9天前更新
安装
API
概览
作者提供的说明（英文原文）
Compliant political SMS/MMS from MCP clients: projects, contacts, analytics, billing.
PopNx MCP 的三大支柱
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。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
- 使用情况i尚未统计★ –
它能帮你做什么
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。
- 连接方式: 在你的电脑上运行
- 传输方式: stdio
- 分类: 营销与社交媒体
- 你需要填写：POLITICAL_COMMS_API_KEY
安装
选择你使用的 AI 应用，然后复制设置。
安装之前
- 基础检查：1 项中通过 1 项
- 在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
- 需要你自己填写：
POLITICAL_COMMS_API_KEY
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
- npm已安装 Node.js（用于 npx 命令）
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": {
"api": {
"command": "npx",
"args": [
"-y",
"@political-comms/mcp"
],
"env": {
"POLITICAL_COMMS_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add api --env POLITICAL_COMMS_API_KEY=your-value -- npx -y @political-comms/mcp运行前请先填写空着的值。
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json
{
"mcpServers": {
"api": {
"command": "npx",
"args": [
"-y",
"@political-comms/mcp"
],
"env": {
"POLITICAL_COMMS_API_KEY": "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。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"api": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@political-comms/mcp"
],
"env": {
"POLITICAL_COMMS_API_KEY": "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。
需要你填写的值
- Political Comms API key (pc_live_*), created by a human operator in the dashboard under Admin > API Keys
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。
它能做什么
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。
基础检查i
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
- ✓ 通过
作者与仓库一致
注册名称已通过域名 politicalcomms.com 验证（注册中心会核实域名所有权）
- … 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- – 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
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“营销与社交媒体”中的其他服务器比较i
- 星标数多于此分类中其他 2959 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 2959 个服务器的 21% 更新
- 基础检查结果等于或优于此分类中其他 2959 个服务器的 100%
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。
常见问题
API 安全吗？
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。
它需要哪些密钥或代码？
你需要填写：POLITICAL_COMMS_API_KEY
它在我的电脑上运行还是在云端？
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）。
它还在维护吗？
GitHub 仓库最后更新于–，最新版本（0.2.1）于3个月前进入注册中心。
哪些应用可以使用它？
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。
有什么可以替代它？
同一分类中有：MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
替代选择
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
Google Analytics MCP
作者：surendranb
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
在你的电脑上运行★ 244MIT9天前更新
安装
BibiGPT YouTube Video Summarizer
作者：JimmyLv
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
在云端运行★ 137MIT9天前更新
安装
作者的 README
打开 README
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。
@political-comms/mcp
MCP (Model Context Protocol) server for the Political Comms REST API. Lets Claude and other MCP clients inspect organizations, projects, contact lists, analytics, and billing, and create, test, and schedule compliant political SMS and MMS sends in the US.
Runs over stdio. Requires Node 20 or later and a Political Comms API key (created in the dashboard under Admin > API, prefixed pc_live_).
Setup
Claude Code
claude mcp add political-comms \--env POLITICAL_COMMS_API_KEY=pc_live_... \ -- npx -y @political-comms/mcp
Claude Desktop
Add to claude_desktop_config.json:
{"mcpServers": { "political-comms": { "command": "npx", "args": ["-y", "@political-comms/mcp"], "env": { "POLITICAL_COMMS_API_KEY": "pc_live_..." } } } }
Tools
Read only:
| Tool | Description |
|---|---|
list_organizations | List organizations visible to the API key. Doubles as a credential check. |
get_hierarchy | Full organization hierarchy tree with brands. |
list_projects | List messaging projects, filterable by organization, brand, or campaign. |
get_project | Full configuration of one project. |
get_project_stats | Delivery and engagement stats for one project. |
get_project_survey_results | Topline survey results for a survey project: per-question option counts and percentages, completion and dropoff rates. Returns a 409 NOT_A_SURVEY error for other projects. |
get_project_throughput | Carrier-limit estimate for one project: recipients per carrier and how long AT&T takes (will_pause is always false). |
get_campaign_throughput | A campaign's T-Mobile daily cap, use today, and AT&T per-minute rates. |
list_contact_lists | Contact lists with counts and status. |
get_contact_list | One contact list with import progress, analysis, and downloads URLs. |
download_contact_list | A contact list as CSV text (type original or analyzed), truncated at 100,000 characters. |
get_message_stats | Aggregate message stats for a date range. |
get_ledger_usage | Billing usage for a date range. |
list_conversations | Conversations with at least one inbound message, sorted by last inbound message. |
get_conversation | One conversation: status, contact, message counts, last activity. |
list_conversation_messages | Messages in one conversation, newest first. |
list_email_domains | Email sending domains and their DNS verification status. |
get_email_domain | One sending domain, including the DNS records to publish. |
list_email_senders | Email sender identities (From addresses). |
list_email_lists | Email lists with contact counts and status. |
list_email_suppressions | Suppressed addresses at org, identity, or list scope. |
list_email_campaigns | Email campaigns with status and audience counts. |
get_email_campaign | One campaign, including blocked: why it will not schedule. |
get_email_campaign_stats | Report tiles and per-link clicks. |
list_email_templates | Saved email templates with subject and last-updated time. |
get_email_template | One template including its full HTML body. |
Write (each is annotated as non read-only; create_project, test_project, schedule_project, and reply_to_conversation additionally require confirm: true because they stage or send real messages):
| Tool | Description |
|---|---|
create_project | Create a draft messaging project. |
test_project | Send real test messages to explicit phone numbers. |
schedule_project | Commit a bulk send at a specific date and time. |
unschedule_project | Remove a project's schedule. |
pause_project | Pause a running or scheduled send; resume with schedule_project. |
copy_project | Copy a project into a new draft (drops lists, schedule, and stats). |
reply_to_conversation | Send a real reply (text, one media_ids entry for MMS, or both) inside an existing conversation. Requires confirm: true. |
schedule_email_campaign | Commit an email send. Requires confirm: true. |
unschedule_email_campaign | Return a scheduled campaign to a draft state. |
start_email_list_import | Import a CSV of contacts into an email list. Requires confirm: true. |
The server deliberately exposes no delete operations.
Email tools
Email write tools need the email entitlement on the organization and return 403 ENTITLEMENT_REQUIRED without it; reads are open. Paid and human-driven email workflows (AI drafting, result exports) and deliverability triage (pausing and resuming a live send) are dashboard features rather than tools: they cost money or need a human watching a send. There is no inbound email or inbox surface.
Errors
API errors are returned as tool errors with the machine readable code and a recovery hint. Rate limited requests (600 requests/minute per key) mention the X-RateLimit-Reset wait; authentication failures explain that a human must create a key in the dashboard.
Full API reference: docs.politicalcomms.com. OpenAPI spec: politicalcomms.com/openapi.json.
License
MIT. Questions: support@politicalcomms.com