Find the most connected/critical symbols in the codebase — those with the highest number of callers and dependencies. These are the riskiest to change.
AI agents call codexray_hotspots to retrieve information from CodeXRay without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
codexray_hotspots performs static analysis and retrieval of code metadata from a semantic knowledge graph. It returns information about code structure and connectivity without modifying, executing, or deleting anything. This is a read-only query operation with no side effects.
From the tool's definition Tool description states it 'Find[s] the most connected/critical symbols' and identifies 'those with the highest number of callers and dependencies' — pure querying/analysis of a pre-built knowledge graph with no modification, deletion, or execution capability.
Documented attack patterns abuse exactly the kind of access codexray_hotspots gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeXRay, and nothing reaches the server without passing your rules. This is the rule we recommend for codexray_hotspots:
{
"version": "1",
"default": "deny",
"tools": {
"codexray_hotspots": {}
}
}codexray_hotspots 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.
Find the most connected/critical symbols in the codebase — those with the highest number of callers and dependencies. These are the riskiest to change. It is categorised as a Read tool in the CodeXRay MCP Server, which means it retrieves data without modifying state.
Register the CodeXRay MCP server in PolicyLayer and add a rule for codexray_hotspots: 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 CodeXRay. Nothing to install.
codexray_hotspots 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 codexray_hotspots 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 codexray_hotspots. 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.
codexray_hotspots is provided by the CodeXRay MCP server (neuralrays/codexray). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeXRay, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 CodeXRay tools catalogued and risk-classified — across an index of 43,000+ MCP servers.