get_latency_analytics
Get latency time-series data with summary.avg_latency_ms, summary.p50_latency_ms, summary.p90_latency_ms, summary.p99_latency_ms, and per-bucket latency percentiles in ms. Use this to spot slowdowns and regressions; use get_cache_hit_latency when you only want cache-hit latency.
This record as markdown: /tools/codeswhat-portkey-admin-mcp/get-latency-analytics.md
What get_latency_analytics does on Portkey Admin
AI agents call get_latency_analytics to retrieve information from Portkey Admin without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_latency_analytics is rated Low
This tool retrieves and queries analytics data (latency metrics and percentiles) without modifying, deleting, or executing any operations. It is a pure data retrieval operation with no side effects. The severity is low because unauthorized access to latency analytics poses minimal risk—it reveals performance metrics rather than sensitive data or system controls.
From the tool's definition Tool description explicitly states it 'Get[s] latency time-series data' and mentions viewing metrics like 'summary.avg_latency_ms', 'summary.p50_latency_ms', etc. No modification, deletion, or execution capabilities are indicated.
Attacks that exploit this kind of access
The rule that runs get_latency_analytics safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Portkey Admin, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_latency_analytics, this is the rule to start with:
get_latency_analytics is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Portkey Admin, apply this rule, and every get_latency_analytics call is checked against it from then on.
Questions about get_latency_analytics
Get latency time-series data with summary.avg_latency_ms, summary.p50_latency_ms, summary.p90_latency_ms, summary.p99_latency_ms, and per-bucket latency percentiles in ms. Use this to spot slowdowns and regressions; use get_cache_hit_latency when you only want cache-hit latency. It is categorised as a Read tool in the Portkey Admin MCP Server, which means it retrieves data without modifying state.
Register the Portkey Admin MCP server in PolicyLayer and add a rule for get_latency_analytics: 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 Portkey Admin. Nothing to install.
get_latency_analytics 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_latency_analytics 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_latency_analytics. 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_latency_analytics is provided by the Portkey Admin MCP server (codeswhat/portkey-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Portkey Admin, and thousands of servers like it.
This server
Across the catalogue