AI agents call project_stats to retrieve information from Codescan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool gathers metrics and statistics about code without creating, modifying, executing, or deleting anything. It is purely informational and read-only in nature. The low severity reflects minimal risk—misuse would only expose existing code metadata.
From the tool's definition Tool 'project_stats' retrieves and queries codebase statistics including 'files by language, line counts, largest files, directory breakdown' with no indication of modification or execution capabilities.
Attacks that exploit this kind of access
Get codebase statistics: files by language, line counts, largest files, directory breakdown. It is categorised as a Read tool in the Codescan MCP Server, which means it retrieves data without modifying state.
Register the Codescan MCP server in PolicyLayer and add a rule for project_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 Codescan. Nothing to install.
project_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 project_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 project_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.
project_stats is provided by the Codescan MCP server (yifanyifan897645/codescan-mcp). 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 →