pdf mcp for Grok
io.github.jztan/pdf-mcp
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
client:Grok
transport:stdio
runtime:pypi
Install pdf mcp in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"pdf-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"pdf-mcp"
],
"env": {
"PDF_MCP_CACHE_DIR": "<PDF_MCP_CACHE_DIR>",
"PDF_MCP_CACHE_TTL": "<PDF_MCP_CACHE_TTL>"
}
}
}
}
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