Update webapp config. Pass keys: server_host, server_port, theme, auto_sync, notifications, llm.
AI agents use config_set to create or update resources in Blender — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Blender environment.
This tool modifies configuration state reversibly. While it changes system behavior (host, port, theme, LLM settings), these changes are not destructive and can be reverted. The ability to change server_host and server_port could affect connectivity and potentially expose security implications, warranting medium severity rather than low.
From the tool's definition Tool description states 'Update webapp config' with specific configuration keys (server_host, server_port, theme, auto_sync, notifications, llm), indicating modification of settings.
Documented attack patterns abuse exactly the kind of access config_set gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Blender, and nothing reaches the server without passing your rules. This is the rule we recommend for config_set:
{
"version": "1",
"default": "deny",
"tools": {
"config_set": {
"limits": [
{
"counter": "config_set_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}config_set 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.
Update webapp config. Pass keys: server_host, server_port, theme, auto_sync, notifications, llm. It is categorised as a Write tool in the Blender MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Blender MCP server in PolicyLayer and add a rule for config_set: 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 Blender. Nothing to install.
config_set 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 config_set 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 config_set. 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.
config_set is provided by the Blender MCP server (sandraschi/blender-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Blender, 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.
77 Blender tools catalogued and risk-classified — across an index of 43,000+ MCP servers.