List supported canonical units by conversion category.
AI agents call list_supported_units to retrieve information from Unit Expert MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool simply enumerates available units for the conversion functionality. It performs a read-only query, returns informational data, and cannot modify, delete, or execute any operations. The blast radius from misuse is negligible—an AI agent calling this repeatedly or with unexpected arguments cannot cause harm beyond wasting computational resources.
From the tool's definition Tool name 'list_supported_units' indicates a retrieval operation. Description states it 'List[s] supported canonical units by conversion category,' which is a query that retrieves information with no side effects.
Attacks that exploit this kind of access
List supported canonical units by conversion category. It is categorised as a Read tool in the Unit Expert MCP MCP Server, which means it retrieves data without modifying state.
Register the Unit Expert MCP server in PolicyLayer and add a rule for list_supported_units: 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 Unit Expert MCP. Nothing to install.
list_supported_units 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_supported_units 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_supported_units. 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_supported_units is provided by the Unit Expert MCP server (kdaehun00/unit-expert-mcp). 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 →