Skip to content
MCP server

vid2context

Pulls transcripts, chapters and metadata from videos so agents can read and cite them

Runs locallyStatus and history
Pricing
Open source
Platforms
CLI, API, Web
Runs
Locally
Version
0.1.1
Listing updated
2 days ago

About vid2context

vid2context is an open-source MCP server for design and media. It runs locally on your machine and is started by your AI client.

Rather than needing a paid transcription API, it works down a fallback chain until text exists. It tries creator captions first, then platform auto-captions, then downloads the audio and runs speech-to-text. Each speech or language-model step is a rung with its own provider and credential, tried in tier order: local models, hosted free tiers using your own key, keyless hosts, and paid APIs last and only when a key is set. Every attempt is logged so you can see what ran.

Output comes as plain text with [m:ss] timestamps, JSON, Markdown, SRT, VTT or a zip, and several videos can be merged into one Markdown pack for upload to ChatGPT Projects or Claude Projects. The README lists YouTube videos, playlists and channels, anything yt-dlp supports, Vimeo, Loom, Wistia, Bilibili, Google Drive, Dropbox and OneDrive links, direct media URLs and local files as inputs.

The same engine ships as an MCP server on npm (vid2context-mcp), a CLI, an HTTP API and a library. API keys for Groq, Gemini, OpenAI, Ollama or a local speech-to-text server are all optional. This is a first release, 0.1.0.

Install

Run in a terminal

claude mcp add vid2context --env GROQ_API_KEY='<GROQ_API_KEY>' --env GEMINI_API_KEY='<GEMINI_API_KEY>' --env OPENAI_API_KEY='<OPENAI_API_KEY>' -- npx -y vid2context-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "vid2context": {
      "command": "npx",
      "args": [
        "-y",
        "vid2context-mcp"
      ],
      "env": {
        "GROQ_API_KEY": "<GROQ_API_KEY>",
        "GEMINI_API_KEY": "<GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "vid2context": {
      "command": "npx",
      "args": [
        "-y",
        "vid2context-mcp"
      ],
      "env": {
        "GROQ_API_KEY": "<GROQ_API_KEY>",
        "GEMINI_API_KEY": "<GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "vid2context": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "vid2context-mcp"
      ],
      "env": {
        "GROQ_API_KEY": "<GROQ_API_KEY>",
        "GEMINI_API_KEY": "<GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "vid2context": {
      "command": "npx",
      "args": [
        "-y",
        "vid2context-mcp"
      ],
      "env": {
        "GROQ_API_KEY": "<GROQ_API_KEY>",
        "GEMINI_API_KEY": "<GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "vid2context": {
      "command": "npx",
      "args": [
        "-y",
        "vid2context-mcp"
      ],
      "env": {
        "GROQ_API_KEY": "<GROQ_API_KEY>",
        "GEMINI_API_KEY": "<GEMINI_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Configuration

  • GROQ_API_KEYOptional. Groq free tier: fast Whisper speech-to-text and LLMs
  • GEMINI_API_KEYOptional. Google AI Studio free tier LLMs
  • OPENAI_API_KEYOptional. OpenAI, used last and only when set
  • OLLAMA_BASE_URLOptional. Local Ollama server, for example http://localhost:11434/v1
  • LOCAL_STT_BASE_URLOptional. Local OpenAI-compatible speech-to-text server, for example http://localhost:8000/v1

What it does

Fallback transcription chain
Uses captions when present, otherwise runs speech-to-text through local, free, keyless and paid rungs in order.
Cited timestamps
Each transcript paragraph carries a time and link so agents can cite the exact moment.
Many sources
Reads YouTube, Vimeo, podcast feeds, cloud-drive links, direct media files and anything yt-dlp supports.
Multiple output formats
Exports text, JSON, Markdown, SRT, VTT or a zip bundle.
Context packs
Combines many videos into one Markdown file for ChatGPT or Claude Projects.
Attempt log
Records every resolve, metadata and caption step so failures are easy to trace.

Good for

  • Let an agent summarise a conference talk and cite the minute a claim was made
  • Turn a playlist of car-buying videos into one searchable research pack
  • Get a transcript of a podcast episode when no captions exist
  • Export subtitles as SRT or VTT for a video

Pricing

Open source

Free and open source; paid APIs used only if you supply a key

Prices change. Check vid2context.com before you buy.

vid2context FAQ

Does it need an API key?

No. It works with zero configuration; keys for Groq, Gemini, OpenAI or a local Ollama server are optional.

What happens when a video has no captions?

It downloads the audio and passes it through the speech-to-text rung chain.

Is it free?

The site calls it free and open source, and paid APIs are only used when you set their key.

Can it run offline?

Local whisper.cpp and Transformers.js are listed for offline speech recognition.

Is vid2context free?

Yes. vid2context is open source, so you can use and self-host it for free.

How do I add vid2context to Claude Code?

Run this command in your terminal: claude mcp add vid2context --env GROQ_API_KEY='<GROQ_API_KEY>' --env GEMINI_API_KEY='<GEMINI_API_KEY>' --env OPENAI_API_KEY='<OPENAI_API_KEY>' -- npx -y vid2context-mcp

What are the best alternatives to vid2context?

The closest alternatives to vid2context are REA, HyperFrames by HeyGen, Codebase Memory, GitHub and Serena MCP: the IDE for your agent.

Alternatives to vid2context

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Hosted MCP connector for creating and rendering videos from HTML through AI chat

    • Remote
    • Freemium
    • 85.3K GitHub stars
    • Design and media
  3. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  4. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  5. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  6. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory