AI agents call codegraph_stats 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 queries and returns aggregate information about a code graph index. It performs data retrieval without creating, modifying, deleting, or executing anything. The read-only nature of statistics—counting entities and relations—poses minimal risk. Even if an AI agent calls this repeatedly, the worst case is wasted compute or rate limiting, not data corruption or unauthorized actions.
From the tool's definition Tool retrieves statistics about an indexed code graph (entity counts, relation counts). The verb 'Get' and the nature of statistics as read-only data indicate no side effects or modifications.
Attacks that exploit this kind of access
Get statistics about the indexed code graph (entity counts, relation counts, etc.). 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 codegraph_stats: 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.
codegraph_stats 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 codegraph_stats 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 codegraph_stats. 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.
codegraph_stats 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 →