MCP server that compresses OCR-heavy PDFs into dense packed images so AI agents can handle long visual documents
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add optical-context -- uvx optical-context-mcp~/.codex/config.toml
[mcp_servers.optical-context]
command = "uvx"
args = ["optical-context-mcp"]
# codex mcp add optical-context -- uvx optical-context-mcp~/.cursor/mcp.json
{
"mcpServers": {
"optical-context": {
"command": "uvx",
"args": [
"optical-context-mcp"
]
}
}
}.vscode/mcp.json
{
"servers": {
"optical-context": {
"type": "stdio",
"command": "uvx",
"args": [
"optical-context-mcp"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"optical-context": {
"command": "uvx",
"args": [
"optical-context-mcp"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"optical-context": {
"command": "uvx",
"args": [
"optical-context-mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"optical-context": {
"command": "uvx",
"args": [
"optical-context-mcp"
]
}
}
}