Suparse Document Processing for Grok
io.github.suparse/suparse-mcp
Extract structured data from PDFs and documents with Suparse AI OCR.
client:Grok
transport:stdio
runtime:npm
Install Suparse Document Processing in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"suparse-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@suparse/mcp"
],
"env": {
"SUPARSE_API_KEY": "<SUPARSE_API_KEY>",
"SUPARSE_API_URL": "<SUPARSE_API_URL>"
}
}
}
}
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