"Loop" matching MCP servers:

Enables agents to report and query performance metrics to build a community-driven quality database for MCP tools. This server helps agents discover and select the most reliable tools based on success rates and user-reported quality scores.

LoopSense is an open-source MCP server that closes the feedback loop for AI coding agents — giving them real-time visibility into CI results, deployments, test outcomes, and file system changes.

Real-machine, real-browser web perf measurement with ~99% iframe coverage. LLM-native + AI-agent-loop ready.

Demonstrates agent-native platform onboarding with human-in-the-loop API key provisioning, plus live usage and rate-limit queries via Anthropic Admin APIs.

Postgres performance MCP server that analyzes hotspots, explains query plans, and detects dead-weight indexes. It aims to produce evidence-backed recommendations through a verification loop.

AgentGuard47 is runtime safety infrastructure for AI agents. It adds budget caps, loop detection, retry limits, timeouts, local traces, and incident reports so agents can stop bad runs while they are happening, not just explain them afterward.

An MCP server for managing MCP server registries with health checks, duplicate detection, and configuration portability. It helps prevent MCP sprawl by tracking server health, identifying overlapping tools, and generating portable configurations for different clients.

Governed Docker + Portainer container-host operations (non-Kubernetes) — restart-loop, resource-pressure, and image/volume-bloat RCA, with guarded lifecycle writes, unbypassable audit logging (MCP + CLI), budget/runaway guards, dry-run, and undo/rollback.

Enables AI agents to investigate Splunk exports or live queries using deterministic detectors and an iterative analysis loop, all running locally without data leaving the machine.

Multi-channel inventory intelligence for Shopify and Amazon sellers. 28 tools for stockout risk, demand forecasts, purchase order management, and sales analytics — with human-in-the-loop safeguards.

Allows AI assistants such as Cursor/Cline/GitHub Copilot to use Google's lighthouse tool to measure perf metrics for your webpage. You can then run an agentic loop and get the assistants to optimize those metrics!

Runaway loop detector for AI token economies — monitors token usage and cost ratios to catch runaway agent loops early.

Provides unified AI agent observability including tracing, cost tracking, performance monitoring, anomaly detection, and audit trails via MCP.

MCP server for tracking and managing costs per AI agent, with budget alerts, anomaly detection, and model cost comparison.

MCP server for writing structured traces, spans, and decisions, enabling observability and EU AI Act traceability compliance for AI agent tasks.

Provides read-only access to OpenClaw and Codex operational data like status, tasks, sessions, logs, and Git changes. Ensures safety via redaction, allowlists, and bounded outputs.

Enables coding agents to access local browser diagnostics—runtime errors, console logs, network failures, breadcrumbs, DOM snapshots, and screenshots—and run closed-loop verification to debug and confirm fixes.

Enables natural language interaction with telecom network operations data via MCP, providing read-only insights and role-gated write operations such as bandwidth upgrades, with progress tracking and human-in-the-loop elicitation.

A Kubernetes diagnostic agent that provides on-demand root cause analysis and human-in-the-loop remediation via Slack, using LLM reasoning with OPA-bounded security controls.

Password-protected dashboard and Remote MCP observer for Codex work, recording concise task milestones via observe_start, observe_report, and observe_finish tools.