list_profiles
AI agents call list_profiles to retrieve information from Mcp Director without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool lists profiles, which is a read-only operation that retrieves data with no side effects. Even though the description is empty, the name clearly indicates enumeration/retrieval rather than creation, modification, or deletion. Severity is low because listing profiles poses minimal risk—it returns configuration data that is not sensitive by nature in this context.
From the tool's definition Tool name 'list_profiles' indicates a query/listing operation with no description provided. Naming convention and sibling tools (apply_profile, create_profile, delete_profile, update_profile) suggest this retrieves profile configurations without modifying…
Attacks that exploit this kind of access
list_profiles. It is categorised as a Read tool in the Mcp Director MCP Server, which means it retrieves data without modifying state.
Register the Mcp Director MCP server in PolicyLayer and add a rule for list_profiles: 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 Mcp Director. Nothing to install.
list_profiles 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 list_profiles 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 list_profiles. 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.
list_profiles is provided by the Mcp Director MCP server (yut0takagi/mcp-director). 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 →