AI agents call decision_search 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 performs a search operation on ADRs (Architectural Decision Records), which is a read-only retrieval function. It queries existing data by keyword and returns results without creating, modifying, deleting, or executing any side effects. The minimal blast radius of a search tool, even if an AI agent uses it incorrectly, makes this low severity.
From the tool's definition Tool name 'decision_search' and description 'Search ADRs by keyword' indicate a query operation that retrieves data without modification.
Attacks that exploit this kind of access
Search ADRs by keyword. 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_search: 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_search 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_search 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_search. 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_search 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 →