Quantifies the scale of the project (Lines of Code).
AI agents call get_code_stats to retrieve information from Code-Oracle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs code analysis and metric collection over local repositories, returning statistics about project scale. It has no side effects—it queries existing code to produce informational output. No code execution, data modification, deletion, or financial impact occurs. Classification as Read is appropriate given the retrieval-only nature and minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_code_stats' and description 'Quantifies the scale of the project (Lines of Code)' indicate a read-only operation that retrieves metrics without modifying, executing, or deleting data.
Attacks that exploit this kind of access
Quantifies the scale of the project (Lines of Code). It is categorised as a Read tool in the Code-Oracle MCP Server, which means it retrieves data without modifying state.
Register the Code-Oracle MCP server in PolicyLayer and add a rule for get_code_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 Code-Oracle. Nothing to install.
get_code_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 get_code_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 get_code_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.
get_code_stats is provided by the Code-Oracle MCP server (sri-lohith-mulugu/oracle-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 →