Query GitHub API call counts and cache hit metrics. Returns a summary of REST calls, GraphQL calls, and cache hits broken down by operation, plus optional raw log entries. Use
AI agents call get_api_metrics to retrieve information from MCP GitHub Issue Priority 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 reports observability metrics about API usage and caching performance. It performs no side effects—no data is created, modified, deleted, or executed. The query operation and metric retrieval are purely informational, making this a Read category tool. Severity is low because misuse would only expose performance telemetry data, not critical system functionality or destructive operations.
From the tool's definition Tool description states it 'Query[s] GitHub API call counts and cache hit metrics' and 'Returns a summary of REST calls, GraphQL calls, and cache hits'. These are retrieval operations with no modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
Query GitHub API call counts and cache hit metrics. Returns a summary of REST calls, GraphQL calls, and cache hits broken down by operation, plus optional raw log entries. Use. It is categorised as a Read tool in the MCP GitHub Issue Priority Server MCP Server, which means it retrieves data without modifying state.
Register the MCP GitHub Issue Priority Server MCP server in PolicyLayer and add a rule for get_api_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 MCP GitHub Issue Priority Server. Nothing to install.
get_api_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_api_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_api_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_api_metrics is provided by the MCP GitHub Issue Priority Server MCP server (steiner385/mcp-git-issue-priority). 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 →