Spoken for Grok
io.github.spokenmd/spoken
Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.
client:Grok
transport:stdio
runtime:npm
Install Spoken in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"spoken": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"spoken-mcp"
],
"env": {
"SPOKEN_API_KEY": "<SPOKEN_API_KEY>"
}
}
}
}
Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs