AI agents call repo_statistics to retrieve information from Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves aggregate information about a git repository (commit counts, branch statistics, contributor metrics, etc.) without creating, modifying, deleting, or executing anything. It is purely informational and poses minimal risk even if an AI agent calls it with arbitrary arguments, since repository statistics are typically non-sensitive aggregate data and the operation cannot alter system state.
From the tool's definition Tool description states it 'Get statistics about a git repository' — a retrieval operation with no modification or side effects. The verb 'Get' and the read-only nature of repository statistics (counts, metrics, metadata) confirm this is a query operation.
Attacks that exploit this kind of access
Get statistics about a git repository. It is categorised as a Read tool in the Memory MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for repo_statistics: 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 Memory. Nothing to install.
repo_statistics 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 repo_statistics 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 repo_statistics. 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.
repo_statistics is provided by the Memory MCP server (shaktisinhchavda/memory-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 →