Optical Context MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 154 installs a week from pypi. Last commit 16 Sep 2026.
Compress OCR-heavy PDFs into dense packed images so agents can work with long visual documents.
Today is the operative word: we check Optical Context MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add optical-context-mcp -- uvx optical-context-mcp
{
"mcpServers": {
"optical-context-mcp": {
"args": [
"optical-context-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.optical-context-mcp]
command = "uvx"
args = ["optical-context-mcp"]
{
"mcpServers": {
"optical-context-mcp": {
"args": [
"optical-context-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"optical-context-mcp": {
"args": [
"optical-context-mcp"
],
"command": "uvx"
}
}
}
Verified OCR with per-value coordinates, plus a workspace agents can file documents into and query.
MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.
Print and mail physical documents in the US via USPS, with quotes, agent payment and tracking.
Local file tools for agents: documents, PDFs, images, QR codes. Nothing is uploaded.
Agent-ready local document context with stable anchors.
Generate PDFs, screenshots, and documents via any MCP-compatible AI agent.
Extract text from documents, manipulate PDFs, and perform OCR on images.
Compose branded visual documents with live preview, data collections, validation, and PDF export.
Answers built from our own checks of this server.