What is vision-mcp AGENTS.md?

Project instructions for vision-mcp, a local MCP server that analyses images. It can detect objects, read text with OCR, and describe layout relationships on Windows, macOS, and Linux without sending images to a cloud service.

Use it when installing, configuring, or maintaining vision-mcp and its Python, YOLOv8, and EasyOCR dependencies.

It documents the software, models, setup, and environment variables needed to run image analysis offline.

How hwalde/vision-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hwalde/vision-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hwalde/vision-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hwalde/vision-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hwalde/vision-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/hwalde/vision-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hwalde/vision-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hwalde/vision-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hwalde/vision-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hwalde/vision-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,816 This file is loaded in full into every session.

When invoked 2,816 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02816	$0.02816
Opus 5.5	$0.01126	$0.01126
Sonnet 5.5	$0.00563	$0.00563
Haiku 4.5	$0.00282	$0.00282

Measured 14d ago against content hash 3c01982bc453, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vision-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 14d 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 · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vision MCP — Setup & Konfiguration

Diese Datei ist die einzige Quelle der Projekt-Doku. CLAUDE.md importiert sie per @AGENTS.md, damit Claude Code sie automatisch mitlädt — nicht duplizieren, hier pflegen.

MCP-Server (Python/FastMCP, stdio oder streamable-http — siehe „Transporte") für Bild-Analyse: Objekterkennung (YOLOv8) und Texterkennung/OCR (EasyOCR), plus abgeleitete Layout-Aussagen (Abstände, Zentrierung). Läuft auf Windows, macOS und Linux, komplett lokal und offline — es geht kein Bild an eine Cloud-API.

Die Ausgabe ist bewusst LLM-optimierter Markdown-Text, kein JSON: natürliche Sätze wie „Text „Headline" liegt 276px oberhalb von person." verarbeitet ein LLM zuverlässiger als verschachtelte Koordinaten-Strukturen.

Was der Server braucht

Baustein	Zweck
Python ≥ 3.10	Laufzeit
Pakete aus `requirements.txt`	u. a. `ultralytics` (YOLO) und `easyocr` — beide ziehen `torch` transitiv mit
YOLOv8-Gewichte (`yolov8n.pt`, ~6 MB)	werden beim ersten Start automatisch geladen
EasyOCR-Sprachmodelle (~100 MB)	werden beim ersten OCR-Aufruf automatisch geladen

Kein API-Key, kein Cloud-Konto, keine Auth. Nur der erste Start braucht Internet, um die Modelle zu holen.

Installation

Nach dem Auschecken genügen zwei Befehle — identisch auf allen Betriebssystemen:

macOS / Linux

pip3 install -r requirements.txt
python3 server.py --selftest

Windows (PowerShell)

pip install -r requirements.txt
python server.py --selftest

--selftest ist der schnellste Weg zur Gewissheit: Er prüft die Python-Version, meldet jedes fehlende Paket namentlich, lädt YOLO- und OCR-Modelle vor (der einzige Schritt, der Internet braucht) und analysiert ein selbst erzeugtes Testbild. Endet er mit „Alles bereit", ist der Server einsatzfähig — man muss den Fehler nicht erst beim ersten Tool-Aufruf im Agenten entdecken. Exit-Code 0 = alles in Ordnung, 1 = Problem.

Read the full file on GitHub · 232 lines

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.

14d ago Changed · +73 lines · +966 tokens per session 3c01982bc453
2mo ago First seen · 159 lines · 1,850 tokens per session scan A f62523745f0f

Subscribe to this mod's changes

vision-mcp AGENTS.md is an instructions file published in the GitHub repository hwalde/vision-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 2,816 tokens to every session, about $0.0113 per session on Opus 5.5. 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.

vision-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vision-mcp AGENTS.mdhwalde/vision-mcp	Instructions file	0	15d ago	MIT	A	2,816	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

vision-mcp: Instructions file for Codex