AI agents call what_breaks to retrieve information from XRAY MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the context of an AST analysis and code mapping server, 'what_breaks' most likely performs impact or dependency analysis to show what code segments would be affected by changes—a Read operation. However, confidence is reduced to 0.6 due to the empty description, which prevents direct verification of the tool's actual behavior.
From the tool's definition Tool name 'what_breaks' with empty description; sibling tools (explore_repo, find_symbol, read_interface) are all Read operations that query code structure without modification; the server is designed for 'structural analysis' and 'code mapping' with no…
Documented attack patterns abuse exactly the kind of access what_breaks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and XRAY MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for what_breaks:
{
"version": "1",
"default": "deny",
"tools": {
"what_breaks": {}
}
}what_breaks is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
what_breaks. It is categorised as a Read tool in the XRAY MCP MCP Server, which means it retrieves data without modifying state.
Register the XRAY MCP server in PolicyLayer and add a rule for what_breaks: 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 XRAY MCP. Nothing to install.
what_breaks 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 what_breaks 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 what_breaks. 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.
what_breaks is provided by the XRAY MCP server (srijanshukla18/xray). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 XRAY MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 XRAY MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.