Answer a natural language question about any public GitHub repo.
AI agents call tool_ask_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 queries and retrieves information from public GitHub repositories without modifying, executing code, or performing destructive actions. It is fundamentally a read operation with no side effects. The scope is limited to public repositories, and the blast radius of misuse is minimal—at worst, repeated queries could cause minor resource consumption but no data loss or financial impact.
From the tool's definition Tool description states it 'Answer[s] a natural language question about any public GitHub repo' — a query operation that retrieves information.
Attacks that exploit this kind of access
Answer a natural language question about any public GitHub repo. 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_ask_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_ask_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_ask_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_ask_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_ask_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 →