Etchv runs on your own machine — the client starts it, so there is no endpoint to ping. 799 installs a week from npm. Last commit 29 Oct 2026.
Invisible watermarking and watermark detection for images, PDFs and videos with Etchv.
Today is the operative word: we check Etchv every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server -e 'ETCHV_API_KEY=<ETCHV_API_KEY>' -e 'ETCHV_FILES_ROOT=<ETCHV_FILES_ROOT>' -- npx -y @etchv-labs/mcp-server
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@etchv-labs/mcp-server"
],
"env": {
"ETCHV_API_KEY": "<ETCHV_API_KEY>",
"ETCHV_FILES_ROOT": "<ETCHV_FILES_ROOT>"
}
}
}
}
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@etchv-labs/mcp-server"]
env = { ETCHV_API_KEY = "<ETCHV_API_KEY>", ETCHV_FILES_ROOT = "<ETCHV_FILES_ROOT>" }
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@etchv-labs/mcp-server"
],
"env": {
"ETCHV_API_KEY": "<ETCHV_API_KEY>",
"ETCHV_FILES_ROOT": "<ETCHV_FILES_ROOT>"
}
}
}
}
{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@etchv-labs/mcp-server"
],
"env": {
"ETCHV_API_KEY": "<ETCHV_API_KEY>",
"ETCHV_FILES_ROOT": "<ETCHV_FILES_ROOT>"
}
}
}
}
Put your own values in place of
<ETCHV_API_KEY> (Etchv API key with the scopes your workflow needs), <ETCHV_FILES_ROOT> (Absolute path of an existing directory for input and output files).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
ETCHV_API_BASE_URL (Optional HTTPS API origin. Defaults to https://api.etchv.com).
Generate and edit images and videos for ecommerce, marketing and advertising with AI-HIVE.
Generate and edit images and videos with imageat.
Detect AI-generated images, videos, and audio with identifAI's deepfake detection tools.
Screenshots, PDFs, OG images, page inspection, and narrated video recording for Claude and Cursor.
PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.
Free deterministic PDF, Markdown, citation, invisible-character, and formatting cleanup for agents.
Quote and create AI images and videos with existing Cocuyo credits and explicit confirmation.
Content moderation for AI applications. Moderate text, images, and video with configurable policies.
Answers built from our own checks of this server.