Full repo audit — overview + dependency health report.
AI agents call tool_audit_repo to retrieve information from Codelens-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only analysis of a public GitHub repository's structure, metadata, and dependency status. It gathers intelligence about the codebase and its dependencies without creating, modifying, deleting, or executing any code. The blast radius of misuse is minimal—worst case, an AI agent wastes time analyzing a repository it shouldn't, with no side effects on any system.
From the tool's definition Tool name 'tool_audit_repo' and description 'Full repo audit — overview + dependency health report' indicate information retrieval and analysis of existing repository state and dependencies.
Attacks that exploit this kind of access
Full repo audit — overview + dependency health report. It is categorised as a Read tool in the Codelens-MCP MCP Server, which means it retrieves data without modifying state.
Register the Codelens- MCP server in PolicyLayer and add a rule for tool_audit_repo: 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 Codelens-MCP. Nothing to install.
tool_audit_repo 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 tool_audit_repo 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 tool_audit_repo. 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.
tool_audit_repo is provided by the Codelens- MCP server (yashkashte5/codelens-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 →