@agentdiscoverability/mcp-analytics
Level CLocalObserve-only analytics for your own MCP server: tool calls, timing, errors and AI-client mix, sent to the AgentDiscoverability collector. End-user identity only through an opt-in identify() hook, no tool-schema changes, fail-open. Fork of the MIT-licensed
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"npm-agentdiscoverability-mcp-analytics": {
"command": "npx",
"args": [
"@agentdiscoverability/mcp-analytics"
]
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://www.npmjs.com/package/@agentdiscoverability/mcp-analytics
Known working client config (can write into mcp.json):
{
"mcpServers": {
"npm-agentdiscoverability-mcp-analytics": {
"command": "npx",
"args": [
"@agentdiscoverability/mcp-analytics"
]
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
NetdataReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anoToolJetOpen-source foundation of ToolJet AI - the enterprise app generation platform fosignozSigNoz is an open-source, OpenTelemetry-native observability platform for your tkuboard-pressKuboard v4 官方文档(zh/en 双语):Kuboard 是基于 Kubernetes 的微服务管理界面。本仓库为 v4 版本文档站源码,涵盖安装升级SkillSpectorSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patternsskillspectorSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patterns