MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Nynch, the AI CRM for consultants and fractionals: contacts, deals and relationship intelligence.
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。
Authorization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
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 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http nynch https://app.nynch.com/mcp --header 'Authorization: your-value'运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"nynch": {
"url": "https://app.nynch.com/mcp",
"headers": {
"Authorization": "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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"nynch": {
"type": "http",
"url": "https://app.nynch.com/mcp",
"headers": {
"Authorization": "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。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 必填 HTTP header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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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 peterod99 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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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。
你需要填写:Authorization
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(3.1.0)于11天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
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。
Website: www.nynch.com · Developer docs: www.nynch.com/developers · Endpoint: https://app.nynch.com/mcp
The official, hosted Model Context Protocol server for Nynch, the AI CRM for consultants and fractionals who win high-value deals based on relationships.
50 tools across 6 categories: CRM read, CRM write, relationship intelligence, firm intelligence, context query, and multi-agent orchestration.
https://app.nynch.com/mcp
Transport: JSON-RPC 2.0 over Streamable HTTP. The server is stateless (no session to manage) and negotiates the protocol version with your client — it speaks 2025-11-25, 2025-06-18, and 2025-03-26.
The older endpoint
https://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-serverstill answers, but it is deprecated. Usehttps://app.nynch.com/mcpin new configs.
In Claude, open Settings → Connectors → Add custom connector and enter https://app.nynch.com/mcp. Click Connect, sign in with your Nynch account and approve access. Revoke access any time in Nynch under Settings → Integrations → AI hosts.
Sign up at www.nynch.com, then go to Settings → Integrations → Claude & AI Assistants and create an API key.
Scopes:
read — Search, browse, and retrieve dataread-write — Read + create, update, delete recordsadmin — Full access including agent orchestrationAdd to claude_desktop_config.json:
{
"mcpServers": { "nynch": { "url": "https://app.nynch.com/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }
Add to .cursor/mcp.json:
{
"mcpServers": { "nynch": { "url": "https://app.nynch.com/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
async with streamablehttp_client( "https://app.nynch.com/mcp", headers={"Authorization": "Bearer YOUR_API_KEY"} ) as (read, write, _): async with ClientSession(read, write) as session: await session.initialize() result = await session.call_tool("search_contacts", {"query": "Acme Corp"}) print(result)
Your AI client discovers available tools automatically. Ask it to search contacts, check your pipeline, create tasks, or analyze relationships.
| Tool | Description |
|---|---|
search_contacts | Search contacts by name, company, or tags |
get_contact_context | Full contact context: profile, interactions, activities, notes, network |
search_deals | Search deals by title, stage, or company |
get_deal_context | Full deal context: stakeholders, learnings, coaching actions |
search_deals_by_inactivity | Find stalled deals with no recent activity |
get_pipeline_summary | Pipeline health: stage distribution, at-risk deals, upcoming closes |
get_next_best_actions | AI-powered recommendations for what to do next |
get_who_list | People to reach now, including identified site visitors. Never mention a specific page in outreach |
list_buckets | List all buckets (lists/segments) |
get_bucket_contacts | Get contacts in a specific bucket |
get_bucket_game_queue | Get contacts waiting to be sorted into buckets |
| Tool | Description |
|---|---|
log_interaction | Record a contact interaction (call, email, meeting, note) |
update_deal_stage | Move a deal to a new pipeline stage |
create_task | Create a task linked to a contact or deal |
create_note | Add a note to a contact (supports markdown) |
create_contact | Create a new contact (auto-links to company by domain) |
update_contact | Update fields on an existing contact |
add_contact_to_bucket | Add a contact to a bucket |
create_deal | Create a new deal in the pipeline |
create_company | Create a new company |
delete_contact | Soft-delete a contact (recoverable) |
bulk_delete_contacts | Soft-delete contacts by tag or ID list |
update_commitment | Mark a commitment as completed or update details |
| Tool | Description |
|---|---|
get_authority_score | Authority score across 6 dimensions |
get_commitments | Commitments with Say/Do tracking and due dates |
get_buying_committee | Stakeholder map: roles, influence, sentiment |
get_contact_signals | Job changes, company changes, buying intent, identified website visits (no page paths) |
get_interaction_history | Full interaction timeline with direction and sentiment |
get_relationship_score | 5-factor relationship strength score |
export_context_briefing | AI-ready context briefing for any contact or deal |
get_relationship_trends | Is engagement growing, stable, or declining? |
get_at_risk_relationships | Contacts with dropping scores or no recent contact |
get_deal_intelligence | Deal health: velocity, stakeholder coverage, risk factors |
get_weekly_briefing | Weekly summary: interactions, changes, recommendations |
| Tool | Description |
|---|---|
get_firm_warm_paths | Who at your firm knows this person or company, ranked by relationship strength. Metadata only, never email content |
find_firm_reachable_people | People you can reach through a teammate, strongest path first, with the best teammate to ask for an intro |
get_firm_client_outcomes | Client work the firm has won: value, retainer, owner, primary contact, referrer, totals by currency |
| Tool | Description |
|---|---|
register_agent | Register an external agent with capabilities and archetype |
list_agents | List registered agents with status |
agent_heartbeat | Confirm agent liveness |
write_context | Write to the shared agent context store |
read_context | Read from context store (supports prefix wildcards) |
create_handoff | Request another agent to perform a task |
get_handoffs | Get pending handoffs for your agent |
complete_handoff | Mark a handoff as completed or failed |
Discover and read bounded slices of Nynch and connected-app context, metadata-first. Read-only — never accepts raw SQL.
| Tool | Description |
|---|---|
list_context_sources | List safe read-only context sources available to you |
search_context_sources | Search context sources by natural-language keyword (metadata only) |
describe_context_source | Describe one source: purpose, columns, filters, limits, availability |
list_context_columns | List selectable columns and allowed filters for one source |
query_context | Read a bounded slice from one source via a constrained query object |
| URI Template | Description |
|---|---|
nynch://contacts/{id} | Full contact context: profile, score, interactions, network |
nynch://deals/{id} | Deal context: details, stakeholders, coaching actions |
nynch://pipeline/summary | Pipeline health overview |
Nynch supports multi-agent workflows where AI agents register, share context, and hand off tasks:
Nynch is the AI CRM for consultants and fractionals who win high-value deals based on relationships. It remembers relationship context across email, meetings and LinkedIn, and surfaces it when a conversation is worth having.
This repository (documentation and configuration) is released under the MIT License. The Nynch MCP Server itself is a hosted service — no local installation required.