"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.

Lets agents query their own usage ledger captured by the Agentic Ledger proxy: sessions with full call traces, costs, loop runs, and stuck-loop flags. Tools include list_sessions, get_session, search, list_runs, get_run_status, and explain.

An MCP server for detecting retry loops and analyzing iteration patterns in agentic coding workflows, providing structured debugging intelligence to improve repair attempts.

Provides MCP tools to create and query SigNoz trace funnels, enabling agents to measure their own step conversion rates from within the agent loop.

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.

A governance and policy enforcement gateway for MCP servers that provides hard guardrails, dynamic parameter bounds, human-in-the-loop approvals, and audit telemetry.

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

An MCP server that provides a governance layer for coding agents, enforcing policies, validation, and human-in-the-loop for tool calls without requiring an API key.

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.

SentinelOps is an MCP server that enables AI-powered security operations with human-in-the-loop safety. It allows agents to investigate threats, propose actions, and execute security responses only after explicit human approval.

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 management of VMware vSphere/ESXi vCenters and standalone hosts across multiple named environments, covering read-only inventory introspection plus policy-gated destructive operations like VM deletion, snapshots, and power actions. Adds a guardrail layer with declarative policy, two-phase confirmation tokens, append-only audit logging, and optional human-in-the-loop web approval.

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

Provides telemetry tools for retrieving recent logs and system metrics to support root-cause analysis of infrastructure incidents. Enables autonomous incident triage with grounded verification and human-in-the-loop remediation.