Visual_Annotation_MCP CLAUDE.md

Visual_Annotation_MCP CLAUDE.md is an instructions file for coding agents from mstocker1/Visual_Annotation_MCP. It costs 450 tokens per session, scanned A, original, MIT.

Project instructions for setting up and using a visual-annotation MCP server with Claude Code. The server uses Playwright, a tool for controlling a browser, to support visual annotation tasks.

In plain words
What is it for?
Use it when installing the server, configuring its project-level MCP connection, launching its browser, or fixing Python, startup-timeout, and tool-visibility issues.
Why use it?
It records setup and troubleshooting steps so the server can start correctly and its tools appear in Claude Code.

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/mstocker1/visual_annotation_mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/mstocker1/Visual_Annotation_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 Visual_Annotation_MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mstocker1/visual_annotation_mcp/claude-md.svg)](https://agentmods.dev/instructions/mstocker1/visual_annotation_mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mstocker1/visual_annotation_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mstocker1/visual_annotation_mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 450 This file is loaded in full into every session.
When invoked 450 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 $0.00450 $0.00450
Opus 5 $0.00225 $0.00225
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 3d ago against content hash 83cd7d81869f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Visual_Annotation_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 3d 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 · 29 lines

What it actually says

Visual Annotation MCP — Claude Code

One-time setup (this repo)

  1. Create a venv and install (from repo root):

    python -m venv .venv

    Windows: .venv\Scripts\pip install -e . then .venv\Scripts\python -m playwright install chromium

    macOS/Linux: source .venv/bin/activate && pip install -e . && python -m playwright install chromium

  2. MCP config is in .mcp.json (project scope). Claude Code may ask you to approve project MCP servers once; if tools do not appear, run claude mcp reset-project-choices and restart.

  3. If the server fails to start because python is not on PATH for the GUI (common on Windows), either:

    • set VISUAL_ANNOTATION_PYTHON to your venv interpreter before starting Claude Code (full path to python.exe or python), or
    • replace the command in .mcp.json with that full path, or
    • on Windows only, point command/args at powershell + -File scripts/run_visual_mcp.ps1 (run from this repo root).
  4. First browser launch can be slow; if needed start Claude with a higher MCP startup timeout, e.g. MCP_TIMEOUT=120000 (units per your shell / Claude docs).

  5. In Claude Code, run /mcp and confirm visual-annotation is connected. Tools: navigate, inspect_elements, screenshot_viewport, screenshot_element, highlight_element, annotate_last_image.

Quick manual test prompt

After opening a project that contains this .mcp.json, ask Claude to: navigate to https://example.com, run inspect_elements, take a viewport screenshot, and describe what it sees.

Optional host allowlist: set VISUAL_ANNOTATION_ALLOWED_HOSTS (comma-separated hostnames, no https://) in the server env block of .mcp.json if you want to restrict URLs.

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. 3d ago First seen · 29 lines · 450 tokens per session scan A 83cd7d81869f

Subscribe to this mod's changes

Visual_Annotation_MCP CLAUDE.md is an instructions file published in the GitHub repository mstocker1/Visual_Annotation_MCP (0 stars, last pushed 4mo ago), licensed MIT. It adds 450 tokens to every session, about $0.0022 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