AI agents invoke ears_to_smt to trigger actions in Musubix. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a transformation/computation — it takes an EARS requirement specification and runs it through a conversion process to produce an SMT-LIB2 formula. While it doesn't modify persistent data, it triggers an external computation/formal verification pipeline whose output depends on the input arguments. This is more than a simple read/query; it executes a formal logic translation process.
From the tool's definition Convert an EARS requirement to SMT-LIB2 formula for formal verification
Attacks that exploit this kind of access
Convert an EARS (Easy Approach to Requirements Syntax) requirement to SMT-LIB2 formula for formal verification. It is categorised as a Execute tool in the Musubix MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Musubix MCP server in PolicyLayer and add a rule for ears_to_smt: 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 Musubix. Nothing to install.
ears_to_smt is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ears_to_smt 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 ears_to_smt. 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.
ears_to_smt is provided by the Musubix MCP server (@nahisaho/musubix-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 →