MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Polymarket smart-money analytics: whale leaderboard, wallet P&L, market consensus, live alerts
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。
ORCALAYER_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
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": {
"orcalayer": {
"command": "uvx",
"args": [
"orcalayer-mcp"
],
"env": {
"ORCALAYER_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add orcalayer --env ORCALAYER_API_KEY=your-value -- uvx orcalayer-mcp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": {
"orcalayer": {
"command": "uvx",
"args": [
"orcalayer-mcp"
],
"env": {
"ORCALAYER_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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"orcalayer": {
"type": "stdio",
"command": "uvx",
"args": [
"orcalayer-mcp"
],
"env": {
"ORCALAYER_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。
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 orcalayer 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。
你需要填写:ORCALAYER_API_KEY
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(0.3.2)于3个月前进入注册中心。
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 Python (uv)。
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。
Model Context Protocol (MCP) server for the OrcaLayer API — Polymarket whale and market analytics inside Claude, Cursor and other MCP clients.
Two ways to use it:
https://orcalayer.com/mcp (Streamable HTTP). Add it as a connector in Claude (Settings → Connectors → Add custom connector, paste the URL) or in any client that supports remote MCP servers.uvx orcalayer-mcp, for Claude Desktop and other local clients.Either way it is a thin wrapper over the orcalayer Python SDK and exposes eight read-only tools:
| Tool | What it does | Key |
|---|---|---|
leaderboard | Rank wallets from the Smart Money set by P&L, win rate, volume or trade count | No |
wallet_overview | Wallet profit tracking: profile, P&L, market win rate, profit factor, rankings | No |
wallet_positions | A wallet's largest open positions | No |
markets | Track smart money flows: search markets and see how many Smart Money wallets hold each side | No |
market_consensus | Smart-money consensus on one market vs its price (head-count + capital-weighted) | No |
whale_alerts | Real-time alerts on profitable wallets: live feed of smart-whale trades | Premium |
pnl_leaderboard | Wallets ranked by realized P&L over the last 7 or 30 days (any window since June 2026) | Premium |
resolution_events | Markets just proposed, disputed, resolved (with the winner) or reopened | Premium |
Public tools work anonymously. whale_alerts, pnl_leaderboard and resolution_events need a Premium API key (get one): on the hosted server send it as the Authorization: Bearer request header (clients that support request headers for a connector), on the local server set the ORCALAYER_API_KEY environment variable. Without a key the tool answers with a short notice, not an error.
Every tool carries readOnlyHint: true: nothing is created, changed or deleted on your behalf. Data is read from the OrcaLayer API only.
Each result carries a short notes block that defines its fields, so a model comparing two tools never meets two different numbers under one name: market_win_rate (share of resolved markets won) has the same basis in leaderboard and wallet_overview; profit_factor is capped at 99.99 on the leaderboard (profit_factor_capped) and uncapped net in the overview; indexed_volume_usd is the volume of fills in OrcaLayer's index, not Polymarket's figure; Smart Money counts are wallets, whatever their size.
New (2026-07-22): the Premium SSE stream (
/api/public/v1/live/trades)
now carries
settlement_type(MINT/MERGE/COMPLEMENTARY/null)
on every event — live-derived settlement mechanics, shadow-verified
100.000% accurate on MINT/MERGE. It describes how the match settled,
not trader intent (~80% of all fills settle as MINT;
null= honest
refusal, not "not a mint"). Details: the
orcalayer://api-reference
resource or orcalayer.com/docs/api.
Ready-to-use prompts for common analytics scenarios:
| Prompt | What it does |
|---|---|
analyze_wallet | Full wallet analysis — smart money or farmer? |
find_divergence | Markets where smart money disagrees with the current price |
hedge_check | Whether a wallet's profit was real alpha or a hedge structure |
territorial_markets_review | Ukraine territorial markets with ISW frontline overlay |
In Claude Desktop, pick a prompt from the prompt menu (the + / slash-command picker) — each one orchestrates the tools above for you.
Read-only context the model can pull directly — no tool call needed:
| Resource URI | Content |
|---|---|
orcalayer://methodology | How smart money is filtered from farmers, hedgers and market-makers |
orcalayer://glossary | Prediction-markets glossary |
orcalayer://api-reference | OrcaLayer REST API reference (endpoints, auth, rate limits) |
Add this to your claude_desktop_config.json (%APPDATA%\Claude\claude_desktop_config.json on Windows, ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": { "orcalayer": { "command": "uvx", "args": ["orcalayer-mcp"] } } }
The public tools work as-is. For the Premium tools (whale_alerts, pnl_leaderboard, resolution_events), add your API key (get one):
{
"mcpServers": { "orcalayer": { "command": "uvx", "args": ["orcalayer-mcp"], "env": { "ORCALAYER_API_KEY": "sk_orca_your_key_here" } } } }
Restart Claude Desktop after editing the config.
The same eight tools, prompts and resources are served at https://orcalayer.com/mcp over Streamable HTTP. No account is needed for the public tools. In Claude: Settings → Connectors → Add custom connector → paste the URL. For the Premium tools, send your Premium key as the Authorization: Bearer request header where your client supports connector headers; keys are never accepted in the URL.
pip install orcalayer-mcp
orcalayer-mcp --http --host 127.0.0.1 --port 8020 --path /mcp
The server is stateless and answers plain JSON, so any reverse proxy with TLS in front of it will do (forward POST /mcp to 127.0.0.1:8020/mcp). The ORCALAYER_MCP_HTTP=1, ORCALAYER_MCP_HOST, ORCALAYER_MCP_PORT and ORCALAYER_MCP_PATH environment variables are equivalent to the flags. ORCALAYER_MCP_ANON_BASE_URL optionally routes anonymous calls to a different API host (the hosted server points it at its local backend); calls that carry a key always go to https://orcalayer.com. Put your own per-client rate limit in the proxy: the server itself does not limit callers.
MIT. See LICENSE.
Data is provided for informational purposes only and is not financial advice.
mcp-name: io.github.orcalayer/orcalayer-mcp