Monitoring & Observability

Capture browser console logs and expose them to AI via MCP — bridges Chrome extension console output to any MCP-compatible IDE

Flight recorder for MCP servers. Wrap any stdio server to log every call with secrets hidden, watch it live in a web viewer, and replay real sessions as regression tests in CI.

Structured CI failure summaries on PRs + compact test/build logs for AI agents. GitHub Action, CLI, MCP. ~80-95% fewer tokens on failures.

End-to-end reliability testing for multi-step AI agent workflows. Tests what DeepEval and Langfuse can't: cascading failures across 10+ step chains.

18 tools: agent memory, API drift detection, and HMAC-signed trust receipts

Wrap agent commands and produce concise, safety-aware run logs.

Official MCP server for IntelliCompli — AML/CTF compliance platform for Australian reporting entities. Connects Claude Desktop and other MCP clients to IntelliCompli's compliance APIs for KYC, sanctions screening, transaction monitoring, and AUSTRAC repor

MCP-native server for Datadog API with tools, resources, prompts, and schema-based generation

Monitor any AI agent system. Auto-detects failures, sends alerts, audits OS processes. Zero config, zero dependencies.

MCP server for JVM diagnostics — analyze thread dumps, detect deadlocks, parse GC logs, and get JVM tuning recommendations

Azure + GCP cost management: spending, forecasts, anomalies, budgets, idle resources, and tags.

SuperBryn MCP server — run the voice-agent eval loop and read your production call logs from Claude Code, Claude Desktop, or Codex.

Diagnoses pg-boss and graphile-worker job queues: retry storms, stuck workers, missed schedules.

Query the Software Observatory catalog of epistemic sensors for software correctness. Built for humans and agents: every command emits JSON with --json.

MCP server for parallel coding agents: detects file contention, coordinates claims, and prevents conflicts between agents working in the same repository.

Scaffold a production-ready Express 5 + TypeScript backend — pick a database + ORM (Postgres/SQLite/Drizzle or Mongo/Mongoose), auth (Auth0/JWT/Clerk), an optional Next.js front end, Sentry, an MCP server, and x402 payments, and get a project with only wh

MCP server for Microsoft Defender for Cloud - secure score, security assessments, regulatory compliance, and attack paths

Agent platform with bitemporal memory, live observability, and audit-grade traceability — for AI that needs to act at the right moment

Argosvix CLI — one-command onboarding for AI agent observability. `npx @argosvix/cli init` authenticates in the browser, installs the SDK, wires the MCP server, and sends a test event.

MCP server for CostHawk - AI API cost monitoring and optimization with Claude Code tracking