Chain of Thought podcast archive

io.github.conorbronsdonPublished by GitHub account conorbronsdonv0.1.0Updated Nov 4, 2026

Search and cite Chain of Thought podcast transcripts and episodes.

The publisher's own server: Agent.chain.tokyo Address Contracts

VerifiedStreamable HTTPWeb executableKnowledge & MemoryMedia & Design

Overview

AI-generated overview

Read-only remote MCP server that lets an assistant search and cite Chain of Thought podcast transcripts and episode metadata.

What you can do
  • Search transcript passages by keyword, with episode, speaker, timestamp and a citable moment URL
  • Find episodes by topic, guest, company or chapter title
  • Fetch one episode's metadata, guests, chapters and page, YouTube and audio links
  • Pull a short run of consecutive transcript segments around a timestamp or search hit
  • Return citation strings and canonical episode URLs for each result
When to use it
Useful when you want an assistant to quote or reference discussions from the Chain of Thought podcast, for example to find what a guest said on a topic and cite the exact moment, or to look up an episode's guests and chapters.
Requirements
A remote Streamable HTTP endpoint at mcp.chainofthought.show; no login, API key, environment variables or headers are needed. Network access to the endpoint is required.
Before you install
Read-only and public, but transcripts are machine-generated and may contain errors, so verify quotations against the recording. Cite the episode page rather than the endpoint; audio and video are not licensed and should be linked, not copied. Results are cached for an hour and new episodes are indexed with a delay.

Installation

In SourceWeft

  1. Open Chain of Thought podcast archive in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.conorbronsdon%2Fchain-of-thought-podcast-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "chain-of-thought-podcast-archive": {
      "type": "http",
      "url": "https://mcp.chainofthought.show/mcp"
    }
  }
}

README

Chain of Thought podcast archive MCP server

This read-only Model Context Protocol server lets AI agents and coding assistants search the transcripts and episode metadata of Chain of Thought, the podcast hosted by Conor Bronsdon, and cite its episode pages. It needs no login or API key. It runs as a Cloudflare Worker with D1 full-text search.

Endpoint

https://mcp.chainofthought.show/mcp is live. The transport is stateless Streamable HTTP. GET / describes the server and GET /health returns ok.

Tools

ToolInputsReturns
search_transcriptsquery (up to 200 characters), limit (1–20, default 8), optional episode (1–9999)Ranked passages with episode, guests, speaker, timestamp, snippet, moment URL and citation.
search_episodesquery (up to 200 characters), limit (1–20, default 8)Ranked episodes with date, guests, summary, matching chapters, URL and citation.
get_episodeepisode (1–9999) or slug (up to 300 characters, including a full episode URL)Metadata, guests, chapters and episode, YouTube and audio links.
get_transcript_excerptepisode (1–9999), optional at (a segment_index from search results, a passage URL or its #t- anchor, m:ss or h:mm:ss), before (0–5, default 2), after (0–10, default 5)Up to 16 consecutive segments with individual URLs, plus anchor and pagination flags.

How search ranks results

Transcript search uses BM25 over passages, with a boost for passages from episodes whose title, guests, chapter titles or summary match the query. Passages containing all query words come before passages containing some. Near-identical passages, such as sponsor reads repeated across episodes, collapse to one result.

A search_transcripts result has this shape (text values abbreviated):

json
{  "episode": 77,  "episode_title": "…",  "guests": ["…"],  "published_at": "…",  "speaker": "…",  "time": "…",  "seconds": 29,  "segment_index": 2,  "snippet": "…",  "match": "all_terms",  "url": "https://chainofthought.show/podcast/…/#t-2",  "episode_url": "https://chainofthought.show/podcast/…/",  "cite": "Chain of Thought, chainofthought.show — https://chainofthought.show/podcast/…/#t-2"}

Connect

These steps follow each vendor's docs as of 2026-10-14. The endpoint must be deployed before a client can connect.

Claude Code

Install in Claude Code

In a Claude Code session, add this repository as a plugin marketplace and install the plugin:

text
/plugin marketplace add conorbronsdon/chain-of-thought-podcast-mcp/plugin install chain-of-thought-podcast@chain-of-thought-podcast-mcp

The plugin connects to the public remote MCP endpoint without an API key. Its optional /chain-of-thought-podcast:cite-chain-of-thought skill helps find and cite podcast discussions.

Add the MCP server directly

Run the Claude Code MCP command:

sh
claude mcp add --transport http chain-of-thought https://mcp.chainofthought.show/mcp

This uses local scope by default. --scope project writes .mcp.json; a project entry is:

json
{"mcpServers":{"chain-of-thought":{"type":"http","url":"https://mcp.chainofthought.show/mcp"}}}

--scope user makes it available across projects.

Claude apps custom connector

In Claude's connector settings, open Customize > Connectors > + Add > Add custom connector. Enter chain-of-thought and https://mcp.chainofthought.show/mcp, select Continue, choose No sign in under Authentication, then select Add. Free plans are limited to one custom connector. On Team plans only Owners and Primary Owners can add connectors; on Enterprise, Owners, Primary Owners and roles with Manage access to Libraries can.

Cursor

Add this to .cursor/mcp.json for a project or ~/.cursor/mcp.json globally, following the Cursor MCP docs:

json
{"mcpServers":{"chain-of-thought":{"url":"https://mcp.chainofthought.show/mcp"}}}

ChatGPT

Open ChatGPT plugins, select the plus button, then Add custom MCP server. Enter chain-of-thought and a description. Under Connection, enter https://mcp.chainofthought.show/mcp. Configure authentication (this server needs none), review the risk warning, select I understand and want to continue, then Create as a plugin and review the discovered tools. A public HTTPS endpoint is required; account and workspace policies apply. See the OpenAI connection guide.

OpenAI plugin ZIP

Build the ChatGPT/Codex upload with npm run package:openai. See OPENAI_PLUGIN.md for validation, brand provenance, ZIP contents, and submission steps.

Citing and usage terms

The source corpus states:

Attribution: "Chain of Thought — chainofthought.show"

Canonical: "Every record carries canonicalUrl. Cite that page, not this endpoint: it is the authoritative rendering and the one that gets corrected."

Transcripts: "Machine-generated (ASR), with entity corrections applied during sync. Transcripts may contain errors; verify quotations against the recording."

License: "CC-BY-4.0"

Audio: "Episode audio and video are not licensed: all rights reserved. The audio and video URLs are links only; link to the episode page instead of copying the media."

Redistribution: "Transcript text and episode metadata are licensed CC BY 4.0 and published as a dataset at https://huggingface.co/datasets/conorbronsdon/chain-of-thought-podcast-transcripts. Credit Chain of Thought (chainofthought.show) and link the episode page."

url is the page to cite; for a transcript passage it includes a #t- anchor to open that segment. The anchor may have one or two numbers and is separate from segment_index. Pass the full URL or its anchor to get_transcript_excerpt to retrieve that passage. episode_url is the episode page without a segment anchor. cite combines attribution and url in the format Chain of Thought, chainofthought.show — <url>.

Limits and freshness

Queries are limited to 200 characters. Search returns 1–20 results (default 8). Snippets are about 600 characters; excerpt segments are at most 1,500 characters, with at most 16 segments per excerpt. No tool returns a whole transcript. Some segments in early episodes 5, 6, 7 and 9 have no timestamp: time and seconds are null, while their URLs still work.

An hourly cron adds, changes or removes at most one episode per run, so a newly published episode is usually indexed within about an hour of appearing in corpus.json when there is no backlog. Successful tool results are cached for one hour; a repeated search can therefore return pre-ingest results for up to about another hour. Transcript corrections are picked up when the round-robin check reaches an episode. At one episode per hour, a full pass over N episodes takes about N/24 days; corpus.json counts.episodes has the current N. Logs record tool name, success, result count and duration. Query text is not logged.

Development

Use Node 22.18 or newer:

sh
npm cinpm run check

npm run check runs typecheck, npm test and validate:openai. npm test runs the vitest suite (test:unit) and then the OpenAI plugin node:test suite (test:openai). The CI workflow runs npm run check on every pull request and on pushes to main. The fixture integration suite below runs in CI only when you start the workflow by hand with integration ticked. For a filtered unit run, use npm run test:unit -- <filter> (for example, npm run test:unit -- test/tools.test.ts); arguments appended to npm test go to the final plugin test runner.

For the three-episode fixture, run these in order, with dev:fixture kept running for the integration test:

sh
npm run build-sql:fixturenpm run db:fixturenpm run dev:fixtureMCP_URL=http://127.0.0.1:8787/mcp npm run test:integration

For the full corpus:

sh
npm run build-sqlnpm run db:fullnpm run dev:fullnpm run query -- --top 3 --compact search_transcripts '{"query":"..."}'npm run eval

To test the cron locally, start wrangler dev --test-scheduled and call:

sh
curl "http://127.0.0.1:8787/__scheduled?cron=23+*+*+*+*"

dist/ and .cache/ hold transcript text and are gitignored. Do not commit or publish them. See Deploying and the design notes.

License

The code in this repository is MIT licensed; see LICENSE. That license does not cover podcast transcripts, episode metadata or other content served by chainofthought.show, which this server reads at runtime. The usage terms above apply to that content.

Source: README.md at commit b3f37c6

Tools

4

search_transcripts

Search transcripts

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.

Parameterslimitqueryrequiredepisode

search_episodes

Search episodes

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.

Parameterslimitqueryrequired

get_episode

Get episode

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.

Parametersslugepisode

get_transcript_excerpt

Get transcript excerpt

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.

Parametersatafterbeforeepisoderequired

Version history

1
  1. v0.1.0LatestOct 14, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Chain integrations

Agent.chain.tokyo Address Contracts

tokyo.chain.agentOfficial publisher

Lets an assistant rent a Japan mailing address for an agent: browse locations and floors, create a 55 USDC payment intent, and track contracts and events.

Streamable HTTPWeb executable
Business & Commerce9 toolsOct 30, 2026

DeviceChain

io.devicechain

Read-only MCP tools for a self-hosted DeviceChain IoT instance, letting an assistant inspect devices, telemetry and alarms.

Streamable HTTPWeb executable
Cloud & InfrastructureNot indexed yetNov 7, 2026

BridgePilot — cross-chain route quotes

Published by GitHub account ert1981

BridgePilot — cross-chain route quotes's hosted MCP server; no sign-in required; Streamable HTTP; 1 tool.

Streamable HTTPWeb executable
1 toolOct 30, 2026

BrainChain

com.usebrainchain

Lets an assistant hand a task brief to a frontier model hired and graded by an AI agent, paying in USDG or USDC only for work that passes the quality levels…

STDIODesktop only
AI & MLNot validated yetNov 7, 2026

Agent Data Tools: Chain data

Published by GitHub account Nutshell2000

Pay-per-call remote MCP server for live blockchain reads: wallet balances, gas, transactions, logs and NFTs on five EVM chains plus Bitcoin.

Streamable HTTPWeb executable
AI & ML200+ toolsNov 7, 2026