Connect Lenny Rachitsky Podcast Transcripts and your agent gets 8 tools, among them getEpisodes, getEpisodesGuest, getEpisodesGuestChunks. It answers at https://lenny-rachitsky.run.mcp.com.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
MCP server for structured access to Lenny Rachitsky podcast transcripts. For content creators.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
getEpisodes | List episodes - Lists episodes with parsed frontmatter (guest, title, duration, youtube_url, etc.) and their canonical resource URIs. Inputs: limit, cursor, sort, x-hapi-auth-state |
getEpisodesGuest | Get an episode card (metadata + key URIs) Inputs: guest, x-hapi-auth-state |
getEpisodesGuestChunks | List chunk descriptors for an episode - Returns chunk boundaries and URIs for chunk retrieval. Chunks may be computed on-demand using size/overlap parameters. Inputs: guest, size, overlap, x-hapi-auth-state |
getEpisodesGuestChunksChunkIdtxt | Get a specific transcript chunk as plain text Inputs: guest, chunkId, x-hapi-auth-state |
getEpisodesGuestMetadatajson | Get episode metadata as JSON (frontmatter) Inputs: guest, x-hapi-auth-state |
getEpisodesGuestTranscriptformat | Get transcript in a specific format - Returns the transcript in the requested format: - md: markdown (may include or exclude frontmatter based on include_frontmatter) - txt: clean text (best for LLM ingestion) - json: structured form (metad Inputs: guest, format, include_frontmatter, x-hapi-auth-state |
getSearch | Search episodes and transcripts - Searches across metadata (D1) and transcript text (Vectorize). Returns matches as resources, including per-hit URIs pointing to episode cards and transcript chunks. Note: pagination cursor applies to metada Inputs: q, mode, episode_slug, guest, title, keywords |
postSearch | Search episodes and transcripts (POST body) - Same search as GET /search, but parameters are provided in the request body. This is useful for longer filter payloads. Inputs: undefinedBody, x-hapi-auth-state |
Every block below points at https://lenny-rachitsky.run.mcp.com.ai/mcp. Pick your client and copy.
claude mcp add --transport http lenny-rachitsky-podcast-transcri https://lenny-rachitsky.run.mcp.com.ai/mcp
{
"mcpServers": {
"lenny-rachitsky-podcast-transcri": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://lenny-rachitsky.run.mcp.com.ai/mcp"]
}
}
}{
"mcpServers": {
"lenny-rachitsky-podcast-transcri": {
"url": "https://lenny-rachitsky.run.mcp.com.ai/mcp"
}
}
}{
"servers": {
"lenny-rachitsky-podcast-transcri": {
"type": "http",
"url": "https://lenny-rachitsky.run.mcp.com.ai/mcp"
}
}
}{
"context_servers": {
"lenny-rachitsky-podcast-transcri": {
"url": "https://lenny-rachitsky.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"lenny-rachitsky-podcast-transcri": {
"serverUrl": "https://lenny-rachitsky.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"lenny-rachitsky-podcast-transcri": {
"url": "https://lenny-rachitsky.run.mcp.com.ai/mcp"
}
}
}name: Lenny Rachitsky Podcast Transcripts
version: 0.0.1
schema: v1
mcpServers:
- name: Lenny Rachitsky Podcast Transcripts
type: streamable-http
url: https://lenny-rachitsky.run.mcp.com.ai/mcp{
"mcpServers": {
"lenny-rachitsky-podcast-transcri": {
"httpUrl": "https://lenny-rachitsky.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"lenny-rachitsky-podcast-transcri": {
"type": "http",
"url": "https://lenny-rachitsky.run.mcp.com.ai/mcp"
}
}
}{
"mcpServers": {
"lenny-rachitsky-podcast-transcri": {
"url": "https://lenny-rachitsky.run.mcp.com.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Flenny-rachitsky.run.mcp.com.ai%2Fmcp&type=streamable_http&id=lenny-rachitsky-podcast-transcri&name=Lenny%20Rachitsky%20Podcast%20Transcripts
It answered our last check on 17 October 2026 in 240 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by com.ai and served from lenny-rachitsky.run.mcp.com.ai, the vendor's own domain: https://lenny-rachitsky.run.mcp.com.ai/mcp.
8, as returned by the server's own tools/list on 7 September 2026: getEpisodes, getEpisodesGuest, getEpisodesGuestChunks, getEpisodesGuestChunksChunkIdtxt, getEpisodesGuestMetadatajson, getEpisodesGuestTranscriptformat, getSearch, postSearch.
It answered our last check on 17 October 2026 in 240 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://lenny-rachitsky.run.mcp.com.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.com.mcp. Endpoint host: lenny-rachitsky.run.mcp.com.ai. ARD identifier: urn:air:ai.com.mcp:mcp:lenny-rachitsky-podcast.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.