Optical Context MCP Server

by chrboebel Your server? Claim it

local only

Optical Context MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 137 installs a week from pypi. Last commit 29 Sep 2026.

Compress OCR-heavy PDFs into dense packed images so agents can work with long visual documents.

Installs per day peak 60 · avg 22 · -3% w/w

a month agotoday

137

Installs / week

pypi · optical-context-mcp

Stars

0 open issues

29 Sep 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

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.

Connect this server

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add optical-context-mcp -- uvx optical-context-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "optical-context-mcp": {
      "command": "uvx",
      "args": [
        "optical-context-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.optical-context-mcp]
command = "uvx"
args = ["optical-context-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "optical-context-mcp": {
      "command": "uvx",
      "args": [
        "optical-context-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "optical-context-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "optical-context-mcp"
      ]
    }
  }
}

Alternatives to Optical Context MCP

same job, measured the same way

MiCompress

by micompress

Compress images, PDFs, video, audio, documents & archives via micompress.com

3 tools answering

doc-convert-mcp

by ioconnex

Document conversion and OCR for AI agents: PDF, Office docs, images to text.

4 tools answering

Space OCR

by hwang-yh-cto

Verified OCR with per-value coordinates, plus a workspace agents can file documents into and query.

answering

PDF Generator MCP

by mrfentmen

Generate PDF documents locally with text, headings, and pages. No network and no key.

98 installs/wk local only

MinerU

by linxule

MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.

196 installs/wk local only

PNG.now MCP Server

by chrisyau83

Compress PNG images and convert them to or from popular image and document formats.

4 tools answering

Razi Document Tools

by razikallayi

Document processing over MCP: merge, split and compress PDFs, run OCR, extract document text.

6 tools answering

Big Documents Agent

by agints

Answers from long PDFs like contracts, leases, and bid packets, with the page number for each point.

answering

Optical Context MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Optical Context MCP?

Optical Context MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package optical-context-mcp was installed 137 times last week.

How do I connect Optical Context MCP?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls optical-context-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Optical Context MCP?

The pypi package optical-context-mcp was installed 137 times in the last week. Week over week that is -3%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Optical Context MCP open source?

Yes — it is published under the MIT licence, written in Python and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.