AI agents use waterMarkFont to create or update resources in Tencent Cloud COS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tencent Cloud COS MCP Server environment.
The tool generates watermarked images, which constitutes creating or modifying data. While the operation itself is reversible (watermarks can be removed or the original image used), it modifies image content and likely uploads results to COS. This fits the Write category.
From the tool's definition Tool name 'waterMarkFont' and description '生成带文字水印的图片' (generate images with text watermarks) indicate the tool creates or modifies image data by adding watermarks. This is a reversible operation that produces new or modified image files.
Documented attack patterns abuse exactly the kind of access waterMarkFont gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tencent Cloud COS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for waterMarkFont:
{
"version": "1",
"default": "deny",
"tools": {
"waterMarkFont": {
"limits": [
{
"counter": "watermarkfont_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}waterMarkFont 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.
生成带文字水印的图片. It is categorised as a Write tool in the Tencent Cloud COS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tencent Cloud COS MCP Server MCP server in PolicyLayer and add a rule for waterMarkFont: 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 Tencent Cloud COS MCP Server. Nothing to install.
waterMarkFont 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 waterMarkFont 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 waterMarkFont. 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.
waterMarkFont is provided by the Tencent Cloud COS MCP Server MCP server (tencent/cos-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Tencent Cloud COS MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Tencent Cloud COS MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.