Agent Content Watermark Mcp

Name: Agent Content Watermark Mcp
Author: CSOAI-ORG

by CSOAI-ORGcommunityv1.1.7

This MCP server provides AI content watermarking with C2PA manifest support for EU AI Act Article 50 compliance. It also supports watermark verification and batch processing for AI-generated content.

From the registry: Agent Content Watermark MCP — dedicated EU AI Act Article 50(2) GenAI watermarking. Visible +

GitHub Repository

Install & configure

Prerequisites

optional
Install uvx (via uv) or Python package tooling
The README config uses `uvx` to run the MCP server. Alternatively, you can install the package with `pip` and run the `agent-content-watermark-mcp` command directly.
```
$ pip install agent_content_watermark_mcp
```
https://pypi.org/project/agent_content_watermark_mcp/'}

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `agent-content-watermark-mcp` MCP server into my current AI client (that's you).

Optional prerequisites:
- Install uvx (via uv) or Python package tooling — The README config uses `uvx` to run the MCP server. Alternatively, you can install the package with `pip` and run the `agent-content-watermark-mcp` command directly. Run: `pip install agent_content_watermark_mcp` (https://pypi.org/project/agent_content_watermark_mcp/'})

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["agent-content-watermark-mcp"]

Note: README provides a stdio configuration using `uvx agent-content-watermark-mcp`. It also states an alternative path: install with `pip install agent-content-watermark-mcp` and run the `agent-content-watermark-mcp` command directly. No environment variables are documented.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: README provides a stdio configuration using `uvx agent-content-watermark-mcp`. It also states an alternative path: install with `pip install agent-content-watermark-mcp` and run the `agent-content-watermark-mcp` command directly. No environment variables are documented.