A local server that lets AI agents take macOS screenshots, target specific windows, and analyse images locally or through a cloud service. MCP is a standard way for an AI agent to call external tools.

Use it to capture screenshots, select windows, and send screen images for AI analysis while an agent works with a Mac desktop.

Agents cannot reliably understand a desktop screen from text alone. This gives them visual access to selected macOS windows and their contents.

peepit-mcp — MCP server for Claude Code and Codex by MantisWare: A local server that lets AI agents take macOS…

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 mcp/mantisware/peepit/peepit-mcp

Clone the repo

git clone --depth 1 https://github.com/MantisWare/peepit

Made for: Claude Code, Codex, Cursor.

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/mcp/mantisware/peepit/peepit-mcp.svg)](https://agentmods.dev/mcp/mantisware/peepit/peepit-mcp)

Your own site

<a href="https://agentmods.dev/mcp/mantisware/peepit/peepit-mcp"><img src="https://agentmods.dev/badge/mcp/mantisware/peepit/peepit-mcp.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

peepit-mcp 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.

listed in the official MCP registry · 9 lines

What it actually says

{ "peepit-mcp": { "command": "npx", "args": [ "-y", "@mantisware/peepit-mcp" ] } }

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.

3d ago First seen · 9 lines scan A 7708feae605c

Subscribe to this mod's changes

peepit-mcp is an MCP server published in the GitHub repository MantisWare/peepit (2 stars, last pushed 1y ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.

Creative and media

mcp-ffmpeg

A Model Context Protocol server for FFmpeg media processing. Runs locally from the mcp-ffmpeg Python package.

kevinten-ai/mcp-ffmpeg · not measured

presentation-md

MCP server exposing all 14 presentation-md tools (render/export/audit/judge/scaffold/share/deploy/import/preview) to any MCP-compatible AI agent. Runs locally from the @presentation-md/mcp-server npm package.

isatimur/presentation-md · not measured

tiktok-instagram-downloader

Extract & download TikTok, Instagram, YouTube, Douyin media — HD, no watermark, MP3 export. Runs locally from the @ssavecc/mcp-server npm package. Needs 1 environment variable to run.

ssavecc/ssave-mcp-server · not measured

after-effects-mcp

MCP server that gives AI assistants deep programmatic control of Adobe After Effects: arbitrary ExtendScript execution, background rendering, deep project/layer inspection, and native Arabic/RTL and multilingual support. Runs locally from the after-effects-mcp npm package.

omar-hesham/after-effect-mcp-with-claude · not measured

tdarr-mcp

MCP server "tdarr-mcp" as configured in hollanbm/tdarr-mcp. Runs locally from the tdarr-mcp Python package.

hollanbm/tdarr-mcp · not measured

agent-canvas

Local MCP canvas for Modellix image generation, editing, task recovery, and visual project work. Runs locally from the @modellix/agent-canvas npm package.

Modellix/modellix-agent-canvas · not measured