ocr-mcp CLAUDE.md

ocr-mcp CLAUDE.md is an instructions file for coding agents from sandraschi/ocr-mcp. It costs 265 tokens per session, scanned A, original, MIT.

Project instructions for ocr-mcp, a Python MCP server that reads text from images and other scanned documents using optical character recognition. They describe its commands, response format, transports, and important files.

In plain words
What is it for?
Use them to run the OCR server or web app, install recognition models, execute tests, and follow the project's MCP response and transport conventions.
Why use it?
They tell a coding agent how this server is started, tested, and structured, reducing mistakes when changing or operating it.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/sandraschi/ocr-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/sandraschi/ocr-mcp

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ocr-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/ocr-mcp/claude-md.svg)](https://agentmods.dev/instructions/sandraschi/ocr-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sandraschi/ocr-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/ocr-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 265 This file is loaded in full into every session.
When invoked 265 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00265 $0.00265
Opus 5 $0.00133 $0.00133
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured 4d ago against content hash baa2fb46d3a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ocr-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 23 lines

What it actually says

ocr-mcp — Claude Code Guide

Overview

FastMCP server providing comprehensive OCR capabilities to the MCP ecosystem

Entry Points

  • uv run ocr-mcpocr_mcp.server:main
  • uv run ocr-mcp-webappocr_mcp.webapp_runner:main
  • uv run ocr-mcp-testscripts.run_tests:main
  • uv run ocr-mcp-install-modelsscripts.install_models:main
  • uv run ocr-mcp-setup-devscripts.setup_dev_env:main

Standards

  • FastMCP 3.2+ portmanteau tool pattern — tools use operation enum param
  • Responses: structured dicts with success, message, domain-specific fields
  • Dual transport: stdio (Claude Desktop) + HTTP (MCP_TRANSPORT=http)
  • See mcp-central-docs for fleet-wide coding standards

Key Files

  • README.md — full documentation
  • pyproject.toml — build config and entry points
  • AGENTS.md — OpenAI Codex agent context (if present)
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 23 lines · 265 tokens per session scan A baa2fb46d3a7

Subscribe to this mod's changes

ocr-mcp CLAUDE.md is an instructions file published in the GitHub repository sandraschi/ocr-mcp (20 stars, last pushed 4d ago), licensed MIT. It adds 265 tokens to every session, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.