AI agents use watermark_text to create or update resources in EU AI Act Compliance MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your EU AI Act Compliance MCP Server environment.
Based on the tool name and server context (content watermarking is explicitly listed in the server description), this tool likely modifies text by embedding watermark metadata or markers. This is a Write operation as it creates/modifies data. Severity is medium since watermarking could alter content in ways that are hard to detect. Confidence is low due to the empty description.
From the tool's definition Tool name 'watermark_text' suggests embedding a watermark into text content; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access watermark_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and EU AI Act Compliance MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for watermark_text:
{
"version": "1",
"default": "deny",
"tools": {
"watermark_text": {
"limits": [
{
"counter": "watermark_text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}watermark_text stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
watermark_text. It is categorised as a Write tool in the EU AI Act Compliance MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the EU AI Act Compliance MCP Server MCP server in PolicyLayer and add a rule for watermark_text: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches EU AI Act Compliance MCP Server. Nothing to install.
watermark_text is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the watermark_text rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for watermark_text. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
watermark_text is provided by the EU AI Act Compliance MCP Server MCP server (sonnylabs/eu_ai_act_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 EU AI Act Compliance MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 EU AI Act Compliance MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.