Transform images using AI with a text prompt and reference images using Meshy AI. Reference Image Input (provide ONE of these): - reference_image_urls (array): 1–5 publicly accessible reference image URLs - reference_file_paths (array): 1–5 absolute paths to LOCAL image files. Server reads and en...
AI agents invoke meshy_image_to_image to trigger actions in Meshy MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external AI operation on Meshy's platform to transform images, which constitutes executing an external process/API call whose effects depend on the input arguments (prompt and reference images). It is not a simple read/write of stored data but an active invocation of an AI image transformation pipeline.
From the tool's definition Transform images using AI with a text prompt and reference images using Meshy AI
Documented attack patterns abuse exactly the kind of access meshy_image_to_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Meshy MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for meshy_image_to_image:
{
"version": "1",
"default": "deny",
"tools": {
"meshy_image_to_image": {
"limits": [
{
"counter": "meshy_image_to_image_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}meshy_image_to_image stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Transform images using AI with a text prompt and reference images using Meshy AI. Reference Image Input (provide ONE of these): - reference_image_urls (array): 1–5 publicly accessible reference image URLs - reference_file_paths (array): 1–5 absolute paths to LOCAL image files. Server reads and encodes them automatically. IMPORTANT: For local files, always use reference_file_paths instead of manually base64-encoding. Other Args: - ai_model (enum):. It is categorised as a Execute tool in the Meshy MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Meshy MCP Server MCP server in PolicyLayer and add a rule for meshy_image_to_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 Meshy MCP Server. Nothing to install.
meshy_image_to_image is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the meshy_image_to_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 meshy_image_to_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.
meshy_image_to_image is provided by the Meshy MCP Server MCP server (meshy-dev/meshy-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Meshy MCP Server, 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.
20 Meshy MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.