Display contents of a PP3 profile in human-readable format.
AI agents call read_profile to retrieve information from Rawtherapee without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and displays the contents of an existing PP3 (RawTherapee profile) file without modifying, deleting, or executing any operations. It is purely informational, making it a Read category tool with low severity—an AI agent querying profile data poses minimal risk.
From the tool's definition Tool name 'read_profile' and description 'Display contents of a PP3 profile in human-readable format' indicate a retrieval operation with no side effects. The verb 'Display' and action of reading profile contents are consistent with data retrieval.
Attacks that exploit this kind of access
Display contents of a PP3 profile in human-readable format. It is categorised as a Read tool in the Rawtherapee MCP Server, which means it retrieves data without modifying state.
Register the Rawtherapee MCP server in PolicyLayer and add a rule for read_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.
read_profile is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_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 read_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.
read_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 →