AI agents call decision_find_by_requirement to retrieve information from Musubix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing decision records based on a search criterion. It performs a read-only query operation with no side effects, reversible modifications, code execution, data deletion, or financial implications. The blast radius of misuse is minimal—an agent could retrieve irrelevant or sensitive ADRs but cannot alter or destroy data.
From the tool's definition Tool name 'decision_find_by_requirement' and description 'Find ADRs related to a requirement' indicate a query/search operation that retrieves Architecture Decision Records (ADRs) matching specified requirements.
Attacks that exploit this kind of access
Find ADRs related to a requirement. It is categorised as a Read tool in the Musubix MCP Server, which means it retrieves data without modifying state.
Register the Musubix MCP server in PolicyLayer and add a rule for decision_find_by_requirement: 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.
decision_find_by_requirement 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 decision_find_by_requirement 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 decision_find_by_requirement. 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.
decision_find_by_requirement 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 →