Calculate repository activity metrics.
AI agents call get_activity_metrics to retrieve information from GitHub Repository Analyzer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and calculates metrics from repository data without creating, modifying, deleting, or executing any operations. It is a pure read operation that returns analytical summaries. Low severity due to no side effects or blast radius; the worst outcome would be inaccurate metrics being returned or presented.
From the tool's definition Tool description states 'Calculate repository activity metrics' with no modification, deletion, or execution capabilities. Name and function indicate read-only aggregation of repository statistics.
Attacks that exploit this kind of access
Calculate repository activity metrics. It is categorised as a Read tool in the GitHub Repository Analyzer MCP Server, which means it retrieves data without modifying state.
Register the GitHub Repository Analyzer MCP server in PolicyLayer and add a rule for get_activity_metrics: 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 GitHub Repository Analyzer. Nothing to install.
get_activity_metrics 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_activity_metrics 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_activity_metrics. 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_activity_metrics is provided by the GitHub Repository Analyzer MCP server (jar285/github_mcp_analyzer). 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 →