vid2context for VS Code
io.github.nirholas/vid2context
Turn any video into context for AI agents: transcripts, metadata, chapters, timestamps.
client:VS Code
transport:stdio
runtime:npm
Install vid2context in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "groq-api-key",
"description": "GROQ_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "gemini-api-key",
"description": "GEMINI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "openai-api-key",
"description": "OPENAI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "ollama-base-url",
"description": "OLLAMA_BASE_URL",
"password": true
},
{
"type": "promptString",
"id": "local-stt-base-url",
"description": "LOCAL_STT_BASE_URL",
"password": true
}
],
"servers": {
"vid2context": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"vid2context-mcp"
],
"env": {
"GROQ_API_KEY": "${input:groq-api-key}",
"GEMINI_API_KEY": "${input:gemini-api-key}",
"OPENAI_API_KEY": "${input:openai-api-key}",
"OLLAMA_BASE_URL": "${input:ollama-base-url}",
"LOCAL_STT_BASE_URL": "${input:local-stt-base-url}"
}
}
}
}VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs