# Remove AI Watermarks (pypi · remove-ai-watermarks)

Identify and remove AI watermarks and provenance metadata from your own images and video.

- Trust score: 72/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- pypi · `remove-ai-watermarks`: 72/100 (this document), [markdown](https://verifymcp.io/servers/wiltodelta-remove-ai-watermarks/remove-ai-watermarks.md), [page](https://verifymcp.io/servers/wiltodelta-remove-ai-watermarks/remove-ai-watermarks)

## Channel facts

- Registry: `pypi`
- Package: `remove-ai-watermarks`
- Version: `0.47.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-24.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 2 of 15 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 405 tokens (~135/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Remove AI Watermarks MCP server?

Remove AI Watermarks runs locally as a PyPI package, launched with uvx remove-ai-watermarks. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add wiltodelta-remove-ai-watermarks -- uvx remove-ai-watermarks
```

### Cursor

```json
{
  "mcpServers": {
    "wiltodelta-remove-ai-watermarks": {
      "command": "uvx",
      "args": [
        "remove-ai-watermarks"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "wiltodelta-remove-ai-watermarks": {
      "command": "uvx",
      "args": [
        "remove-ai-watermarks"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add wiltodelta-remove-ai-watermarks -- uvx remove-ai-watermarks
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "wiltodelta-remove-ai-watermarks": {
      "type": "local",
      "command": [
        "uvx",
        "remove-ai-watermarks"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add wiltodelta-remove-ai-watermarks --command uvx --arg remove-ai-watermarks
```

### Hermes

```yaml
mcp_servers:
  wiltodelta-remove-ai-watermarks:
    command: "uvx"
    args: ["remove-ai-watermarks"]
```

### Netclaw

```json
{
  "McpServers": {
    "wiltodelta-remove-ai-watermarks": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "remove-ai-watermarks"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add wiltodelta-remove-ai-watermarks -t stdio -c uvx -a remove-ai-watermarks
```

### Other

```json
{
  "mcpServers": {
    "wiltodelta-remove-ai-watermarks": {
      "command": "uvx",
      "args": [
        "remove-ai-watermarks"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-24 (score 72, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-23 (score 57, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.47.0 → 0.47.1

### 2026-10-21 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 70, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-19 (score 55, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.46.0 → 0.47.0

### 2026-10-18 (score 69)

First indexed and scored.

## MCP tools (3)

### `identify` (~90 tokens)

Identify AI provenance

Report which AI provenance signals an image or video carries: metadata (C2PA, IPTC, EXIF, TC260), visible AI-generator labels, and supported local invisible-watermark decoders. Read-only. Video is detected by file suffix.

Input parameters:

- `check_visible` (boolean): Run the pixel and visible-mark detectors. False reads metadata only.
- `path` (string, required): Image or video file to inspect.

### `remove` (~123 tokens)

Remove AI watermarks from one file

Write a cleaned copy of an image or video the user generated or edited. mode=metadata strips AI metadata without touching pixels or re-encoding video; mode=visible also removes a known visible AI label; for an image, mode=all adds the invisible-watermark scrub where the installed extras and hardware allow it. The source is never overwritten; the default output is <name>_clean beside it.

Input parameters:

- `mode` (string)
- `output` (string): Output file. Must differ from the source.
- `path` (string, required): Image or video file to clean.

### `batch` (~91 tokens)

Remove AI watermarks from a directory

Clean every supported image (media=image) or video (media=video) in a directory the user owns, writing results to a separate directory (default <dir>_clean). Modes as for the remove tool.

Input parameters:

- `directory` (string, required): Directory of input files.
- `media` (string)
- `mode` (string)
- `output_dir` (string): Output directory. Must differ from the input.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/wiltodelta-remove-ai-watermarks/remove-ai-watermarks#diagnostics

## Score history

- 2026-10-24: 72
- 2026-10-23: 57
- 2026-10-22: 71
- 2026-10-21: 71
- 2026-10-20: 70
- 2026-10-19: 55
- 2026-10-18: 69

## Common questions

### What is the Remove AI Watermarks MCP server?

Remove AI Watermarks is an MCP server listed in the public MCP registry as io.github.wiltodelta/remove-ai-watermarks. Identify and remove AI watermarks and provenance metadata from your own images and video. This page covers its PyPI package (remove-ai-watermarks).

### Is the Remove AI Watermarks MCP server safe to use?

Remove AI Watermarks scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Remove AI Watermarks MCP server expose?

Remove AI Watermarks exposes 3 tools: identify, remove, batch. Their descriptions and schemas cost roughly 304 tokens of context every time the server is loaded.

### Is the Remove AI Watermarks MCP server still maintained?

Remove AI Watermarks is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Remove AI Watermarks MCP server under?

Remove AI Watermarks declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/remove-ai-watermarks/
- Socket report: https://socket.dev/pypi/package/remove-ai-watermarks
- Repository: https://github.com/wiltodelta/remove-ai-watermarks
- Website: https://github.com/wiltodelta/remove-ai-watermarks/blob/main/docs/mcp-server.md
- Changelog RSS feed: https://verifymcp.io/servers/wiltodelta-remove-ai-watermarks/remove-ai-watermarks.xml
- Changelog JSON feed: https://verifymcp.io/servers/wiltodelta-remove-ai-watermarks/remove-ai-watermarks.json
- HTML version of this page: https://verifymcp.io/servers/wiltodelta-remove-ai-watermarks/remove-ai-watermarks