Get detailed metrics per author
AI agents call get_author_metrics to retrieve information from Git Metrics MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing git repository data (author-level metrics) without creating, modifying, deleting, or executing operations. It is purely informational analysis of historical repository metadata. The read operation has minimal blast radius if misused—worst case is exposure of development team metrics/performance data.
From the tool's definition Tool name 'get_author_metrics' and description 'Get detailed metrics per author' indicate a retrieval operation.
Attacks that exploit this kind of access
Get detailed metrics per author. It is categorised as a Read tool in the Git Metrics MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Git Metrics MCP Server MCP server in PolicyLayer and add a rule for get_author_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 Git Metrics MCP Server. Nothing to install.
get_author_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_author_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_author_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_author_metrics is provided by the Git Metrics MCP Server MCP server (jonmatum/git-metrics-mcp-server). 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 →