vid2context
● Activeio.github.nirholas/vid2context
Turn any video into context for AI agents: transcripts, metadata, chapters, timestamps.
Connect this server
One click to install, or copy the config below. Suits: Claude Desktop · Cursor.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"vid2context": {
"command": "npx",
"args": [
"-y",
"vid2context-mcp@0.2.0"
],
"env": {
"GROQ_API_KEY": "<your GROQ_API_KEY>",
"GEMINI_API_KEY": "<your GEMINI_API_KEY>",
"OPENAI_API_KEY": "<your OPENAI_API_KEY>"
}
}
}
}claude mcp add --env GROQ_API_KEY='<your GROQ_API_KEY>' --env GEMINI_API_KEY='<your GEMINI_API_KEY>' --env OPENAI_API_KEY='<your OPENAI_API_KEY>' --transport stdio vid2context -- npx -y vid2context-mcp@0.2.0codex mcp add vid2context --env GROQ_API_KEY='<your GROQ_API_KEY>' --env GEMINI_API_KEY='<your GEMINI_API_KEY>' --env OPENAI_API_KEY='<your OPENAI_API_KEY>' -- npx -y vid2context-mcp@0.2.0code --add-mcp '{"name":"vid2context","type":"stdio","command":"npx","args":["-y","vid2context-mcp@0.2.0"],"env":{"GROQ_API_KEY":"<your GROQ_API_KEY>","GEMINI_API_KEY":"<your GEMINI_API_KEY>","OPENAI_API_KEY":"<your OPENAI_API_KEY>"}}'Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.
- GROQ_API_KEYsecretOptional. Groq free tier: fast Whisper speech-to-text and LLMs
- GEMINI_API_KEYsecretOptional. Google AI Studio free tier LLMs
- OPENAI_API_KEYsecretOptional. OpenAI, used last and only when set
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Media & Creative
- Version
- 0.2.0
- Registry
- active
- Published
- 11/19/2026
Live check
checked Nov 19, 2026, 06:07 UTCThe endpoint is up but wants a key or an OAuth sign-in before the handshake, so its tools can only be read with an account.
Checked by Serverdex with a plain initialize + tools/list call to vid2context.com/mcp, no credentials, about once a day. A failed check is never a removal.
On GitHub
read Nov 15, 2026- Stars
- 2
- Forks
- 1
- Last push
- Nov 15, 2026
- License
- Apache-2.0
TypeScriptai-agentscaptionsclicontext-engineeringgemini-cli-extensionhttp-apillmlocal-llmmcpmcp-servermodel-context-protocolragspeech-to-texttranscripttypescriptvideo-to-textvideo-transcriptionwhisperyoutubeyoutube-transcript
From the README
vid2context Turn any video into context for AI agents. An MCP server, CLI, HTTP API and library that gives Claude, ChatGPT, Cursor, VS Code Copilot and any other agent the transcript, metadata and chapters of a video, playlist, podcast or media file, with timestamps it can cite. Paste a video link or drop in a media file. vid2context returns the transcript, metadata and chapters in a form your agent can read and cite: plain text with [m:ss] timestamps, JSON, Markdown, SRT, VTT, or one Markdown context pack for many videos that you can upload to ChatGPT Projects, Claude Projects or a custom GPT. It is free first. Local models run first, then hosted free tiers with your own key, then keyless hosts that need no account. Paid APIs are used last, and only when you set their key. With zero configuration it already works. The web app on an 18 minute YouTube video: paste the link, then copy or download the transcript, captions, chapters or a context pack sized for an agent. Recorded live against the local API. MP4 version. Why Research happens on video. A playlist explaining which used car to buy, a conference talk, a course, a podcast. Agents cannot watch any of it. vid2context turns those videos into text with timestamps, so an agent can absorb a whole series and answer "which model year should I buy?" while citing the episode and the moment that said so. Design rule: raw transcripts are always kept.…
Read the full README on GitHub →Remotes
- streamable-http
https://vid2context.com/mcp
Alternatives to vid2context
Best Media & Creative servers →The most-starred Media & Creative servers in the index, with their live-check result.
| Server | Stars | Last push | Live check |
|---|---|---|---|
| HyperFrames by HeyGen | 86,475 | Nov 2026 | Needs sign-in |
| HyperFrames by HeyGen | 84,441 | Nov 2026 | Needs sign-in |
| Pascal 3D Editor | 25,495 | Nov 2026 | Needs sign-in |
| screenpipe | 22,421 | Nov 2026 | Local / not checked |
| FunASR | 21,030 | Nov 2026 | Local / not checked |
vid2context: questions people ask
- Is vid2context a remote or a local MCP server?
- According to its entry in the official MCP registry, vid2context ships as a hosted endpoint (streamable-http) that your client connects to by URL and as a local package (npm) that your client starts on your machine. Use the hosted endpoint when your client supports Streamable HTTP; use the package when you want it to run locally.
- Does vid2context need an API key or a sign-in?
- Yes. Its hosted endpoint answered the credential-free Serverdex live check with HTTP 401/403 on Nov 19, 2026: it expects an API key in a header or an OAuth login before it lists its tools.
- Is vid2context still maintained?
- Active: the repository's last commit 4 days ago. Last push Nov 15, 2026, 2 GitHub stars, Apache-2.0 licence. Read from GitHub on Nov 15, 2026.
- How do I add vid2context to Claude, Cursor or VS Code?
- Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
More Media & Creative servers
Browse all Media & Creative →Ytranscript MCP
nnnoel
YouTube transcripts and video details for AI tools. No proxies; transcribes captionless videos.
No License Nearby
NoBanks
Search 880+ artist-owned tracks and get sync licenses for social, TV and film.
Shotcut MCP
NoBanks
Edit video through Shotcut's MLT engine: timelines, cuts, filters, titles, crossfades and renders.
noncelogic MCP
noncelogic
Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
Tubescout
not0lucky
YouTube as a research engine: keyless search, video intel, resilient transcripts, demand signals.
Wan27 MCP — AI Image and Video Generation
NotUsingGithub
Generate AI images and videos, estimate credits and track tasks. Paid Wan27 subscription required.
Add the badge to your site
Show visitors that vid2context is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-nirholas-vid2context?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="vid2context — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-nirholas-vid2context?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.