Save a texture resource to an image file. Args: resource_id: The texture resource ID string. output_path: Absolute path for the output file. file_type: Output format: png, jpg, bmp, tga, hdr, exr, dds (default: png). mip: Mip level to save (default 0). Use -1 for all mips (DDS only). event_id: Op...
AI agents use save_texture to create or update resources in Renderdoc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Renderdoc environment.
This tool creates new files on disk (image exports of textures in various formats: png, jpg, bmp, tga, hdr, exr, dds). While file creation is reversible (files can be deleted), it modifies the filesystem state and could consume disk space or overwrite existing files if the output_path conflicts. This is a Write action rather than Read-only since it produces persistent artifacts.
From the tool's definition The tool description states it 'Save[s] a texture resource to an image file' with parameters for output_path and file_type, indicating file creation/modification on the filesystem.
Documented attack patterns abuse exactly the kind of access save_texture gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Renderdoc, and nothing reaches the server without passing your rules. This is the rule we recommend for save_texture:
{
"version": "1",
"default": "deny",
"tools": {
"save_texture": {
"limits": [
{
"counter": "save_texture_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_texture 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.
Save a texture resource to an image file. Args: resource_id: The texture resource ID string. output_path: Absolute path for the output file. file_type: Output format: png, jpg, bmp, tga, hdr, exr, dds (default: png). mip: Mip level to save (default 0). Use -1 for all mips (DDS only). event_id: Optional event ID to navigate to first. It is categorised as a Write tool in the Renderdoc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Renderdoc MCP server in PolicyLayer and add a rule for save_texture: 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 Renderdoc. Nothing to install.
save_texture 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 save_texture 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 save_texture. 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.
save_texture is provided by the Renderdoc MCP server (linkingooo/renderdoc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Renderdoc, 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.
42 Renderdoc tools catalogued and risk-classified — across an index of 43,000+ MCP servers.