Chain of Thought podcast archive
Search and cite Chain of Thought podcast transcripts and episodes.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"chain-of-thought-podcast-mcp": {
"url": "https://mcp.chainofthought.show/mcp"
}
}
}远程端点
https://mcp.chainofthought.show/mcpstreamable-http它能做什么
工具清单
工具（4）
🟢search_transcripts(query, limit, episode)
Full-text search over Chain of Thought transcripts. Returns up to 20 passages ranked by relevance, each with episode number and title, guests, speaker, timestamp, a snippet of about 600 characters, and a url for that moment on the episode page (#t-N). Cite that url. Optional `episode` limits the search to one episode. Use get_transcript_excerpt for context. Transcripts are machine-generated; check exact quotes against the recording.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 200,
"description": "Words to find in transcript passages."
},
"limit": {
"default": 8,
"description": "Maximum passages, 1 to 20.",
"type": "integer",
"minimum": 1,
"maximum": 20
},
"episode": {
"description": "Restrict to this episode number.",
"type": "integer",
"minimum": 1,
"maximum": 9999
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢search_episodes(query, limit)
Finds Chain of Thought episodes by topic, guest name, company, title or chapter title. Returns up to 20 episodes ranked by relevance with number, title, date, guests, a short summary, matching chapter titles and the episode page url to cite.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 200,
"description": "Topic, guest, company, title or chapter words."
},
"limit": {
"default": 8,
"description": "Maximum episodes, 1 to 20.",
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"required": [
"query"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_episode(episode, slug)
Returns one episode by number or slug (a full chainofthought.show episode URL also works): title, date, duration, guests with companies, summary, chapters with timestamps, and links to the episode page, YouTube and audio. Does not return the transcript; use search_transcripts or get_transcript_excerpt for passages. Cite the url.
输入模式
{
"type": "object",
"properties": {
"episode": {
"description": "Episode number.",
"type": "integer",
"minimum": 1,
"maximum": 9999
},
"slug": {
"description": "Episode slug or full chainofthought.show episode URL.",
"type": "string",
"maxLength": 300
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_transcript_excerpt(episode, at, before, after)
Returns up to 16 consecutive transcript segments from one episode around a timestamp (m:ss or h:mm:ss), a segment_index from search results, or a passage url or its #t- anchor. Defaults: 2 segments before and 5 after. Each segment has its own url to cite.
输入模式
{
"type": "object",
"properties": {
"episode": {
"type": "integer",
"minimum": 1,
"maximum": 9999,
"description": "Episode number."
},
"at": {
"description": "Segment index from search results, passage URL or #t- anchor, m:ss or h:mm:ss.",
"type": "string",
"maxLength": 300
},
"before": {
"default": 2,
"description": "Segments before the anchor, 0 to 5.",
"type": "integer",
"minimum": 0,
"maximum": 5
},
"after": {
"default": 5,
"description": "Segments after the anchor, 0 to 10.",
"type": "integer",
"minimum": 0,
"maximum": 10
}
},
"required": [
"episode"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}社区
证据