Videre-MCP AGENTS.md

Videre-MCP AGENTS.md is an instructions file for Codex, OpenCode from Veedubin/Videre-MCP. It costs 2,150 tokens per session, scanned A, original, MIT.

Agent instructions for videre-mcp, a server that lets text-only coding models understand images by converting them into written descriptions. It supports general image descriptions, text extraction from images and descriptions of screen layouts.

In plain words
What is it for?
Use it to describe photos and diagrams, extract text from screenshots or documents, understand user-interface layouts, take a screenshot, or perform higher-accuracy multilingual OCR.
Why use it?
It supplies visual information when the coding model cannot directly see an image, screenshot, diagram or scanned document.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions OpenCode.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/jcharles/Projects/python/videre-mcp/.venv/bin/python.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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.

agentmods badge for Videre-MCP AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/veedubin/videre-mcp/agents-md.svg)](https://agentmods.dev/instructions/veedubin/videre-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/veedubin/videre-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/veedubin/videre-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,150 This file is loaded in full into every session.
When invoked 2,150 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 5.1 $0.02150 $0.02150
Opus 5 $0.01075 $0.01075
Sonnet 5 $0.00430 $0.00430
Haiku 4.5 $0.00215 $0.00215

Measured 5d ago against content hash 95ef6950f89e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Videre-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 5d 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 · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

videre-mcp Agent Guide

What videre-mcp Does

videre-mcp is an MCP server that lets text-only coding models see images. It loads a local Florence-2 vision model and exposes six tools that convert images, SVGs, and screenshots into structured text descriptions.

Screenshot → videre-mcp (Florence-2) → Text description → Your coding model

Your coding model doesn't need vision capabilities — videre-mcp handles the vision part and returns plain text.

When to Use Each Tool

Tool Use When Don't Use When
describe_image You need to know what's in a photo, diagram, or illustration You need text extraction (use ocr_image)
ocr_image You need to extract text from an image (code screenshots, documents, error messages) You need to understand UI layout (use describe_screenshot)
describe_screenshot You need to understand a UI layout — what buttons, fields, panels are on screen and where You need a general description of a photo
take_screenshot You need to see what's currently on screen AND understand it You already have a screenshot file
ocr_paddle You need high-accuracy OCR for multi-language documents You need simple English OCR (use ocr_image)
parse_document You need to extract structured content from PDF/DOCX/PPTX You need to describe an image (use describe_image)

Tool Reference

describe_image(image_path, detail_level="normal", model_mode="fast")

Returns a natural language description of the image contents.

  • detail_level="normal" → brief caption (e.g. "A white dog sitting on a couch")
  • detail_level="high" → detailed description (e.g. "A small white dog with floppy ears sitting on a brown leather couch in a sunlit living room...")

Return format:

{
  "description": "...",
  "model": "Florence-2-base",
  "prompt_used": "<DETAILED_CAPTION>"
}

ocr_image(image_path, detail_level="normal", model_mode="fast")

Extracts text from an image.

Read the full file on GitHub · 217 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.

  1. 5d ago First seen · 217 lines · 2,150 tokens per session scan A 95ef6950f89e

Subscribe to this mod's changes

Videre-MCP AGENTS.md is an instructions file published in the GitHub repository Veedubin/Videre-MCP (0 stars, last pushed 12d ago), licensed MIT. It adds 2,150 tokens to every session, about $0.0107 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.

Related

Other instructions, from other repositories