Save the current render target(s) at a specific event. Args: event_id: The event ID to capture the render target from. output_path: Output file path or directory. If directory, auto-names the file. save_depth: Also save the depth target (default False).
AI agents use save_render_target 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 and writes image files to disk (render targets are GPU textures converted to file format). While file writing is reversible and doesn't constitute destructive deletion, it modifies the file system by creating new files. The 'Write' category is appropriate as it creates/exports data without irreversible consequences.
From the tool's definition Tool name 'save_render_target' and description 'Save the current render target(s)' indicate file creation/writing operations. Parameters include 'output_path' for specifying where files are written, and optional 'save_depth' flag to include additional data.
Documented attack patterns abuse exactly the kind of access save_render_target 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_render_target:
{
"version": "1",
"default": "deny",
"tools": {
"save_render_target": {
"limits": [
{
"counter": "save_render_target_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_render_target 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 the current render target(s) at a specific event. Args: event_id: The event ID to capture the render target from. output_path: Output file path or directory. If directory, auto-names the file. save_depth: Also save the depth target (default False). 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_render_target: 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_render_target 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_render_target 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_render_target. 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_render_target 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.