Talkthrough runs on your own machine — the client starts it, so there is no endpoint to ping. 222 installs a week from pypi. Last commit 23 Oct 2026.
Local MCP server: recordings or public video URLs into transcript, frames, OCR, wall-clock evidence.
We read the source, 6 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
proc = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add talkthrough-mcp -- uvx talkthrough-mcp
{
"mcpServers": {
"talkthrough-mcp": {
"command": "uvx",
"args": [
"talkthrough-mcp"
]
}
}
}
[mcp_servers.talkthrough-mcp]
command = "uvx"
args = ["talkthrough-mcp"]
{
"mcpServers": {
"talkthrough-mcp": {
"command": "uvx",
"args": [
"talkthrough-mcp"
]
}
}
}
{
"servers": {
"talkthrough-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"talkthrough-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
TALKTHROUGH_WHISPER_MODEL (Whisper model (tiny|base|small|medium|large-v3|large-v3-turbo). Default: small. Use large-v3-turbo for non-English narration; the process_media `model` param overrides per call), TALKTHROUGH_OCR (Set to 'off' to disable OCR of keyframes. Default: on), TALKTHROUGH_OCR_LANG (Recognition script for on-screen text: a language code (ru, ja, ko, ar, hi, ...) or a RapidOCR pack name (eslav, cyrillic, ...). Default: Latin+Chinese), TALKTHROUGH_HOME (Job store root. Default: ~/.talkthrough), TALKTHROUGH_MAX_DOWNLOAD_BYTES (Hard cap for one process_url download. Default: 2147483648 (2 GiB)).
Any social-video URL → transcript, metadata, frames, OCR, summary, search, Q&A. MCP server + x402.
MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.
Turn bug screen recordings into chronological context for AI agents: frames, OCR, logcat, voice.
Turn public social video links into local, navigable PDF references.
39 AI tools: transcription, video description, image & video generation, TTS, music, OCR via deAPI
Files to text for AI agents: audio/podcast transcription, OCR, video frames, screenshots, web to MD.
Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.
Local AI vision MCP server for Windows: OCR, chart analysis, scene description. 100% offline.
Answers built from our own checks of this server.