Talkthrough runs on your own machine — the client starts it, so there is no endpoint to ping. 1 622 installs a week from pypi. Last commit 6 Sep 2026.
Local MCP server: recordings or public video URLs into transcript, frames, OCR, wall-clock evidence.
We read the source, 21 h ago · rules 3dff92dd89df
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.
return subprocess.run(cmd, check=True, capture_output=True, text=True, timeout=timeout)
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": {
"args": [
"talkthrough-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.talkthrough-mcp]
command = "uvx"
args = ["talkthrough-mcp"]
{
"mcpServers": {
"talkthrough-mcp": {
"args": [
"talkthrough-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"talkthrough-mcp": {
"args": [
"talkthrough-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
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).).
The author declared them in the registry entry; get the values from the project itself.
Any social-video URL → transcript, metadata, frames, OCR, summary, search, Q&A. MCP server + x402.
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.
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.
Local-first MCP server + CLI that turns PDFs into source-linked, card-based HTML readers.
Search US local-government meetings: AI summaries, transcripts, and adopted plan documents.
Convert files, URLs, and documents to clean, AI-ready Markdown via MCP.
Answers built from our own checks of this server.