update_base_profile
AI agents use update_base_profile to create or update resources in Rawtherapee — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rawtherapee environment.
This tool modifies configuration data (a profile) reversibly rather than executing arbitrary operations or deleting data. The 'update' verb signals a Write action. Severity is high because corrupting or maliciously modifying a base profile used across multiple photos could degrade image quality or workflow for all subsequent edits.
From the tool's definition Tool name 'update_base_profile' indicates modification of a base profile configuration used in RAW photo development. Within a photo editing context, updating profiles affects processing parameters applied to images.
Attacks that exploit this kind of access
update_base_profile. It is categorised as a Write tool in the Rawtherapee MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rawtherapee MCP server in PolicyLayer and add a rule for update_base_profile: 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 Rawtherapee. Nothing to install.
update_base_profile 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 update_base_profile 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 update_base_profile. 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.
update_base_profile is provided by the Rawtherapee MCP server (lucamarien/rawtherapee-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →