Optical Context MCP for Grok
io.github.chrboebel/optical-context-mcp
Compress OCR-heavy PDFs into dense packed images so agents can work with long visual documents.
client:Grok
transport:stdio
runtime:pypi
Install Optical Context MCP in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"optical-context-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"optical-context-mcp"
]
}
}
}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