skills.rest
GobbyAI
GobbyAIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

metrics

Retrieve and present MCP tool usage metrics and performance data in tables.

19|3|Updated Dec 15, 2025
Search Tags:#performance#monitoring#analytics#metrics#tool-usage#gobby
One-click install
npx skills add https://github.com/GobbyAI/gobby --skill metrics-gobbyai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: metrics
Source: https://github.com/GobbyAI/gobby/tree/main/src/gobby/install/shared/skills/metrics
Command: npx skills add https://github.com/GobbyAI/gobby --skill metrics-gobbyai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides visibility into how MCP tools are used and how they perform, helping teams monitor reliability and identify bottlenecks in real time.

Core Features & Use Cases

  • Tool usage statistics: Retrieve per-tool call counts, success rates, and latency to assess overall tool health.
  • Top tools by usage: Rank tools by usage to prioritize optimization and capacity planning.
  • Identify failing tools: Detect tools exceeding failure thresholds to trigger remediation.
  • Per-tool success rate: Obtain detailed success rates for a specific server and tool combination.
  • Maintenance & retention: Reset or cleanup metrics and inspect retention statistics to manage data growth.

Quick Start

Use the metrics command to view current tool usage: /gobby metrics tools See top tools by usage: /gobby metrics top Check a specific tool's success rate: /gobby metrics success gobby-tasks create_task

Frequently Asked Questions about metrics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor MCP tool usage and check success rates?▼

To monitor MCP tool usage, you can retrieve per-tool call counts, success rates, and latency using the metrics commands. This provides visibility into tool health and helps identify bottlenecks in real time.

What is the best way to identify failing tools in my server?▼

Identifying failing tools involves detecting tools that exceed defined failure thresholds. You can use the metrics command to check for failing tools and trigger remediation based on the detected failures.

Can I filter tool performance metrics by server name and project ID?▼

Yes, you can filter tool performance metrics. The retrieval commands support optional filters for server name, tool name, and project ID, allowing you to narrow down the performance data to specific contexts.

How do I manage metrics data growth and check retention statistics?▼

Managing metrics data growth involves resetting or cleaning up old metrics and inspecting retention statistics. These maintenance commands help control data size and ensure your monitoring data remains manageable.

How can I rank tools by usage to prioritize optimization?▼

You can rank tools by usage to prioritize optimization by retrieving top tools. The metrics command formats these results into clear tables, showing which tools are most frequently used for capacity planning.

Related Skills

Explore More Data & Analytics Skills→
Snowflake-LabsSnowflake-Labs
12

read-ors-configuration

A concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略

Official
Intermediate
wrsmith108wrsmith108
5

performance-analysis

Detect and remediate performance bottlenecks in Claude Flow swarms.

Community
Intermediate
alangebalangeb

tau_audit

Parse AI agent audit logs to identify bottlenecks, errors, and anomalies.

Community
Advanced
nikhillinitnikhillinit

tech-debt-tracker

Detect and prioritize technical debt with configurable thresholds and SQALE metrics.

Community
Advanced