AI agents use draw_texts to create or update resources in 🪄 ImageSorcery MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 🪄 ImageSorcery MCP environment.
Based on the tool name 'draw_texts' and context from sibling tools (draw_arrows, draw_circles, draw_lines, draw_rectangles) which all appear to be image manipulation/drawing tools, this tool likely draws or overlays text onto an image. This is a Write operation as it modifies image data. Confidence is reduced due to the empty description.
From the tool's definition Tool name is 'draw_texts'; description is empty or uninformative.
Documented attack patterns abuse exactly the kind of access draw_texts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 🪄 ImageSorcery MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for draw_texts:
{
"version": "1",
"default": "deny",
"tools": {
"draw_texts": {
"limits": [
{
"counter": "draw_texts_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}draw_texts 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.
draw_texts. It is categorised as a Write tool in the 🪄 ImageSorcery MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 🪄 ImageSorcery MCP server in PolicyLayer and add a rule for draw_texts: 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 🪄 ImageSorcery MCP. Nothing to install.
draw_texts 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 draw_texts 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 draw_texts. 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.
draw_texts is provided by the 🪄 ImageSorcery MCP server (sunriseapps/imagesorcery-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 🪄 ImageSorcery MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 🪄 ImageSorcery MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.