Convert between magnetic units (T↔Gauss, Wb↔Maxwell, A/m↔Oersted, H↔mH↔uH)
AI agents call unit_convert to retrieve information from Magnetics SME MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a pure mathematical conversion between unit systems with no side effects, no data written, no external operations triggered. It simply takes a value in one unit and returns the equivalent in another unit — a read/compute-only operation.
From the tool's definition Convert between magnetic units (T↔Gauss, Wb↔Maxwell, A/m↔Oersted, H↔mH↔uH)
Attacks that exploit this kind of access
Convert between magnetic units (T↔Gauss, Wb↔Maxwell, A/m↔Oersted, H↔mH↔uH). It is categorised as a Read tool in the Magnetics SME MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Magnetics SME MCP Server MCP server in PolicyLayer and add a rule for unit_convert: 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 Magnetics SME MCP Server. Nothing to install.
unit_convert 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 unit_convert 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 unit_convert. 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.
unit_convert is provided by the Magnetics SME MCP Server MCP server (jkearney126/maxwell_bot). 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 →