Compress a single local image file using TinyPNG API (only supports image files, not folders)
AI agents use compress_local_image to create or update resources in Image Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Image Tools environment.
This tool modifies an existing local image file by compressing it via the TinyPNG API. This is a Write operation as it overwrites/modifies the file content, though it may be partially reversible if the original is preserved. The severity is medium because it modifies local files, potentially overwriting original image data.
From the tool's definition Compress a single local image file using TinyPNG API
Documented attack patterns abuse exactly the kind of access compress_local_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Image Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for compress_local_image:
{
"version": "1",
"default": "deny",
"tools": {
"compress_local_image": {
"limits": [
{
"counter": "compress_local_image_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}compress_local_image 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.
Compress a single local image file using TinyPNG API (only supports image files, not folders). It is categorised as a Write tool in the Image Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Image Tools MCP server in PolicyLayer and add a rule for compress_local_image: 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 Image Tools. Nothing to install.
compress_local_image 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 compress_local_image 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 compress_local_image. 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.
compress_local_image is provided by the Image Tools MCP server (kshern/image-tools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Image Tools, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Image Tools tools catalogued and risk-classified — across an index of 43,000+ MCP servers.