by blursecdev
Official Model Context Protocol (MCP) server for @blursec/sdk — lets AI agents check credentials, tokens, and sessions against live stealer-log threat intel.
npm:@blursec/mcp · local package74/wkpublished 4 mo ago
Logs, metrics, traces and alerts.
Official Model Context Protocol (MCP) server for @blursec/sdk — lets AI agents check credentials, tokens, and sessions against live stealer-log threat intel.
Local-first dashboard + MCP for Claude Code and Codex token usage. Per-MCP/tool breakdown.
Real-time observability for AI coding agents — Claude Code & OpenCode. Track tokens, costs, tool calls, agents, MCP, sessions, quotas and orchestration locally.
Unofficial MCP server for New Relic via NerdGraph: query telemetry from AI agents with a User API key
Redis health, BullMQ queue monitoring, memory analysis, and slow query diagnostics
MCP server for AgentLens — instrument AI agents with zero code changes
Website maintenance checks: domains, SSL, uptime, technical SEO and accessibility
Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
Model Context Protocol server for Helicone observability platform
Track and query EzStat metrics from Claude, Cursor, or any MCP agent. StatHat-compatible.
Records MCP tool calls and itemises the token cost each server adds to your context.
A comprehensive MCP server for NewRelic — 25 tools for NRQL, entities, alerts, dashboards, logs, and more
Embedded Manifest observability server — self-hosted AI agent monitoring with SQLite, zero external dependencies
Local post-hoc forensics and postmortems for coding-agent runs
X-ray vision for AI agent sessions — a transparent HTTP proxy and dashboard for Claude Code
Server operations MCP: HTTP health checks, log analysis, deploy dry-runs, mail diagnostics.
Agent observability: structured logging, cost tracking, and compliance audit trails
120-module QA gate. Give Claude eyes (screenshots), ears (Sentry errors), and hands (verify fixes).
Sentry MCP server for any MCP-compatible AI client (Claude Code, Codex, Antigravity, Cursor, etc.) - fetch issues, search errors, resolve/ignore issues, get stack traces and breadcrumbs
Analyze Convai sessions, latency, reliability, usage, and provider telemetry via API key.