AI agents call codegraph_query 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.
The tool performs a query/search operation on a code graph data structure to find entities based on filters like type, name pattern, and file path. This is a retrieval operation with no side effects - it does not create, modify, delete, or execute any code or external operations. The use of 'Query' combined with the criteria-matching pattern clearly indicates a Read operation that returns data about the code graph.
From the tool's definition Tool description states 'Query the code graph for entities matching specific criteria' - this is a read-only operation that retrieves information about code entities without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Query the code graph for entities matching specific criteria (type, name pattern, file path, 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_query: 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_query 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_query 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_query. 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_query 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 →