A
arcmira/mcp
YouTube transcript search for your AI. Find who said what with timestamps, mentions, sponsors, and recommendations. Remote MCP and agent skills.
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
编辑补写Arcmira requires sign-in through an OAuth-capable MCP client or an account API key; it does not work anonymously.
MCP setup: https://arcmira.com/docs/mcp-server
API docs: https://arcmira.com/docs
MCP setup: https://arcmira.com/docs/mcp-server
API docs: https://arcmira.com/docs
安装与配置
远端端点(Claude Desktop / Cursor / Windsurf 共用 mcpServers)
{
"mcpServers": {
"arcmira-mcp": {
"url": "https://mcp.arcmira.com/mcp"
}
}
}把这段粘进 Claude Desktop / Cursor 的 mcpServers 配置即可。端点来自公开证据,我们没有替你安装或托管它。 官方 Registry 记录:这个端点列了请求头 Authorization(Bearer <key>. An arc_sk_ account key from arcmira.com; with no account, POST https://api.arcmira.com/v1/signups with an email address and ve),但没有标为必填。能不能匿名连上,以项目文档为准。
VS Code(.vscode/mcp.json —— 键名是 servers,远程要 type: http)
{
"servers": {
"arcmira-mcp": {
"type": "http",
"url": "https://mcp.arcmira.com/mcp"
}
}
}VS Code 的配置文件和另外三家不同:顶层键是 <code>servers</code>,远程端点还要写 <code>"type": "http"</code>。复制到 .vscode/mcp.json。
Claude Code(命令行)
claude mcp add --transport http arcmira-mcp https://mcp.arcmira.com/mcp
Claude Code 不收 JSON 文件,用这条命令直接加。
配置项的键名以你的客户端为准:客户端与 CLI
- 来源明细
- 收录自 abordage/awesome-mcp 榜单(我们从中收集的条目之一) · 条目类型:MCP 服务
- 收录与活跃
- 收录于 2026-11-03 · 最近见到 2026-11-14 · 共见到 12 次 · 被 12 个来源列出
- 评分构成
- 综合分 1,200 · 12 个来源 · mcp
常见问题(答案都来自我们的记录)
怎么安装?
我们【没有】从该仓库取到安装命令(我们的 install 覆盖率只有约 4%)。请看它的 README 或 releases 页。
它适合谁 / 用来做什么?
我们把它归在这些标签下: MCP 服务。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
我们收录于 2026-11-03;最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。
# Arcmira MCP for YouTube and podcast transcript search
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Search YouTube video and podcast transcripts, retrieve timestamped quotes, find entity mentions and media appearances, inspect organic endorsements and ad reads, and monitor new mentions with your agent.
Arcmira · API docs · MCP setup
## Connect Arcmira
Add the remote MCP server at https://mcp.arcmira.com/mcp and sign in through your host. For setup instructions, use Connect your agent.
For a coding agent, paste:
text
Fetch and execute the appropriate instructions to set me up for Arcmira from https://arcmira.com/agent-setup/prompt.md
## Run your first search
Ask your agent:
> Search YouTube and podcast transcripts for GPU financing over the last 60 days. Return the relevant quotes with speakers when available, publication dates, transcript sources, and timestamped links. Read the surrounding exchanges before summarizing what the sources imply.
The agent calls arcmiradescribe once to load the client reference, then runs a program with arcmiraexecuteread. Return structured fields for further analysis and a compact, sourced answer for the reader.
javascript
const query = "GPU financing";
const hits = await arcmira.search({
query, after: arcmira.daysAgo(60), before: arcmira.today(), limit: 5,
});
return { query, window: hits.window, passages: hits.chunks };
The search supports up to 20 passages, but full passages can exceed the execute tool's output budget. If the result is truncated, request fewer passages or return only the fields needed for the next step. Keep selected text intact and retain its source link.
## Choose the method for the task
| Task | Client method | What to retain |
| Search YouTube and podcast transcripts for quotes | arcmira.search | Passage text, attribution when available, publication date, watch URL |
| Read the surrounding transcript | arcmira.transcript | State, timestamped lines, source, speaker mapping |
| Find mentions of a person, company, product or topic | arcmira.mentions | Entity, description, source video, position, appearance flag |
| Count a person's media appearances | arcmira.occurrences with mode: "appearances" | Counted window, episode counts by channel |
| Compare mention momentum | arcmira.momentum | Current/prior counts, change, verdict, returned window |
| Find organic endorsements or ad reads | arcmira.recommendations | Classification, verbatim quote, source and position |
| Find recurring channel sponsors | arcmira.sponsors | Sponsor, ad-read count, video count, first/latest dates |
| Set up YouTube monitoring | arcmira.monitors through arcmiraexecutewrite | Monitor, tracked entities, delivery settings |
Resolve names before applying entity or channel ID filters. Plain keyword search does not need a resolver call. The MCP client's argument names differ from the HTTP and SDK names; use the reference returned by arcmiradescribe.
## Continue the research
Continue the investment research workflow. You will learn how to follow a search result into competing explanations, inspect the surrounding exchange, verify claims against disclosures, and write a brief with the questions that remain unresolved.
Speaker identification and commercial classifications can be incomplete. Check the linked source. Missing a source or a capability your workflow needs? Use arcmirafeedback to describe it, why it matters, and what better support would be worth. Help shape the index.
Arcmira · API docs · MCP setup
## Connect Arcmira
Add the remote MCP server at https://mcp.arcmira.com/mcp and sign in through your host. For setup instructions, use Connect your agent.
For a coding agent, paste:
text
Fetch and execute the appropriate instructions to set me up for Arcmira from https://arcmira.com/agent-setup/prompt.md
## Run your first search
Ask your agent:
> Search YouTube and podcast transcripts for GPU financing over the last 60 days. Return the relevant quotes with speakers when available, publication dates, transcript sources, and timestamped links. Read the surrounding exchanges before summarizing what the sources imply.
The agent calls arcmiradescribe once to load the client reference, then runs a program with arcmiraexecuteread. Return structured fields for further analysis and a compact, sourced answer for the reader.
javascript
const query = "GPU financing";
const hits = await arcmira.search({
query, after: arcmira.daysAgo(60), before: arcmira.today(), limit: 5,
});
return { query, window: hits.window, passages: hits.chunks };
The search supports up to 20 passages, but full passages can exceed the execute tool's output budget. If the result is truncated, request fewer passages or return only the fields needed for the next step. Keep selected text intact and retain its source link.
## Choose the method for the task
| Task | Client method | What to retain |
| Search YouTube and podcast transcripts for quotes | arcmira.search | Passage text, attribution when available, publication date, watch URL |
| Read the surrounding transcript | arcmira.transcript | State, timestamped lines, source, speaker mapping |
| Find mentions of a person, company, product or topic | arcmira.mentions | Entity, description, source video, position, appearance flag |
| Count a person's media appearances | arcmira.occurrences with mode: "appearances" | Counted window, episode counts by channel |
| Compare mention momentum | arcmira.momentum | Current/prior counts, change, verdict, returned window |
| Find organic endorsements or ad reads | arcmira.recommendations | Classification, verbatim quote, source and position |
| Find recurring channel sponsors | arcmira.sponsors | Sponsor, ad-read count, video count, first/latest dates |
| Set up YouTube monitoring | arcmira.monitors through arcmiraexecutewrite | Monitor, tracked entities, delivery settings |
Resolve names before applying entity or channel ID filters. Plain keyword search does not need a resolver call. The MCP client's argument names differ from the HTTP and SDK names; use the reference returned by arcmiradescribe.
## Continue the research
Continue the investment research workflow. You will learn how to follow a search result into competing explanations, inspect the surrounding exchange, verify claims against disclosures, and write a brief with the questions that remain unresolved.
Speaker identification and commercial classifications can be incomplete. Check the linked source. Missing a source or a capability your workflow needs? Use arcmirafeedback to describe it, why it matters, and what better support would be worth. Help shape the index.
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/arcmira-mcp/)
- 来源
- awesome · https://github.com/arcmira/mcp
- 按领域浏览
- MCP 服务
- 收录来源
- 12 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。