agentmods.dev

easyocr-mcp AGENTS.md

Repository instructions for an EasyOCR server that lets an AI assistant read text from images. It covers the server's files, tools, setup, and language settings.

In plain words
What is it for?
Maintaining the EasyOCR MCP server, using its tools for images supplied as files, URLs, or base64 data, and running its tests.
Why use it?
It gives the coding agent the project-specific context needed to work safely in the repository instead of guessing how the OCR server is organized or configured.

Instructions file for CodexOpenCode

2 4mo ago A scan 371 tokens original Apache-2.0
View the source file WindoC/easyocr-mcp
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/windoc/easyocr-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/WindoC/easyocr-mcp

Made for: Codex, OpenCode.

Per session 371 This file is loaded in full into every session.
When invoked 371 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 $0.00371 $0.00371
Opus 5 $0.00186 $0.00186
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash d11c4bd62dd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

easyocr-mcp AGENTS.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 2d 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.

AGENTS.md · 39 lines

What it actually says

AGENTS.md — easyocr-mcp

This repository contains an MCP (Model Context Protocol) server that provides OCR using EasyOCR. Details below mirror what exists in this repo and its README.

Scope

  • Applies to this repository rooted here.

Overview

  • Name: EasyOCR MCP Server
  • Purpose: Provide OCR tools via EasyOCR for images (base64, file, URL).
  • Entry point: easyocr-mcp.py

Current Files (key)

  • easyocr-mcp.py — MCP server and OCR tools.
  • README.md — Features, install, usage, configuration, examples.
  • pyproject.toml — Project metadata and dependencies.
  • test.py, test-gpu.py, test_mcp_tools.py — Local test scripts.
  • test.png — Sample image.
  • LICENSE, .gitignore, uv.lock, plan.md — Licensing, ignores, lockfile, notes.

Tools (as implemented)

  • ocr_image_base64 — OCR from base64-encoded image.
  • ocr_image_file — OCR from an image file path.
  • ocr_image_url — OCR from an image URL.

Configuration

  • Environment: EASYOCR_LANGUAGES — comma-separated language codes (default en).

Install & Run (see README for details)

  • Optional GPU (PyTorch): see README for the exact uv pip install ... command.
  • Install deps and run:
    • uv sync
    • uv run easyocr-mcp.py
    • Example tests: uv run test.py, uv run test-gpu.py

MCP Client Config

  • See README section “MCP Configuration Example” for Windows and Linux/macOS JSON snippets.
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. 2d ago First seen · 39 lines · 371 tokens per session scan A d11c4bd62dd8

Subscribe to this mod's changes

easyocr-mcp AGENTS.md is an instructions file published in the GitHub repository WindoC/easyocr-mcp (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 371 tokens to every session, about $0.0019 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 2026-08-31.

Data and AI
Related

Other instructions, from other repositories

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

Azure/GPT-RAG · 207 tokens

OpenCandle AGENTS.md

Instructions for Kahtaf/OpenCandle, covering opencandle, commands, where to look, code style and conventions.

Kahtaf/OpenCandle · 1,628 tokens

oci-agent CLAUDE.md

Instructions for Netflix-Skunkworks/oci-agent, covering observational causal inference (oci) agent and rules.

Netflix-Skunkworks/oci-agent · 143 tokens

ZipAI CLAUDE.md

Claude Code instructions for nickdesi/ZipAI, covering claude.md — zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.

nickdesi/ZipAI · 1,204 tokens

TreeSkill CLAUDE.md

Instructions for JimmyMa99/TreeSkill, covering claude.md, project overview, commands, install and run tests.

JimmyMa99/TreeSkill · 1,248 tokens

AutoRAG-Research CLAUDE.md

Instructions for NomaDamas/AutoRAG-Research, covering claude.md, project overview, common commands, setup and code quality.

NomaDamas/AutoRAG-Research · 1,477 tokens