"An open-source penetration testing framework" matching MCP servers:

A framework for building MCP servers with built-in enterprise capabilities such as authentication, authorization, telemetry, audit logging, and data classification, allowing domain developers to focus on business logic while maintaining governance and compliance.

Enables AI agents to debug and repair historical Solaris/SPARC systems by providing an out-of-band control plane with guest DTrace, QEMU monitor access, SPARC-aware GDB, host eBPF/perf tracing, and an immutable evidence ledger for cross-layer hypothesis testing.

Runtime constitutional verification for AI answers — claim extraction with reasoning chains, Epistemic Confidence Score (ECS), 7-angle Glassbox Court red team, constitution compilation, Trust Card assembly, and deterministic SHA-256 audit logs.

Enables AI agents to browse and filter experiment runs, retrieve metrics, logs, tables, and artifacts, plot comparisons as PNG images, and download full-fidelity training history for local analysis against a self-hosted Open Train server. It also provides diagnostic tooling that surfaces metric evidence and investigation leads without asserting causality.

Multi-machine system monitor with a built-in MCP server that enables AI agents to query health metrics, manage processes, schedule cron jobs, and run diagnostics across local and remote machines.

Radar is an open-source Kubernetes observability and diagnostics MCP server. It exposes cluster health, workload diagnosis, logs, events, topology, audit findings, and remediation actions to AI agents through the Model Context Protocol.

MCP-native LLM observability. Query your Spanlens traces, stats, cost anomalies, and savings from Cursor, Claude Desktop, or any MCP client. Open source (MIT).

Open-source MCP server for Umami Analytics — Cloud and self-hosted.

Read-only-by-default MCP server for Datanika, an open-source dlt + dbt-core data pipeline platform: browse connections, introspect and preview source tables, compile and run dbt transformations, and monitor pipeline runs. 25 tools (17 read-only, plus 8 write tools gated behind --allow-write); source lives in the datanika-mcp/ subdirectory of the repo.

Open-source .NET framework and server for Model Context Protocol (MCP) with enterprise OAuth 2.0/OIDC auth, per-tool MFA, OpenTelemetry, and health checks.

A specialized diagnostic framework that enables AI models to self-diagnose and fix MCP-related issues by analyzing logs, validating configurations, testing connections, and implementing solutions.

An open-source MCP server that collects errors from browser console and terminal, then uses OpenRouter's free AI models to generate summaries for AI agents.

An open-source MCP server that protects AI agents at runtime by evaluating every tool call against YAML policies and generating audit trails.

An MCP server that gives your AI assistant full awareness of your local dev environment — running processes, Docker containers, git state, open ports, log files, and more.

Open-source MCP gateway connecting AI agents like Claude Desktop and Claude Code to SuiteCRM. 24 CRM tools over SSE with OAuth2/OIDC auth, multi-entity support, ACL enforcement, and Prometheus/Grafana observability.

An open source MCP server empowering SREs with intelligent observability, predictive analytics, and AI-driven automation across Kubernetes, OpenShift, and Tekton environments.

A minimal guardrails framework for AI agents, acting as an MCP proxy to enforce policies, approvals, and audit logging on tool calls.

An open-source, vendor-agnostic MCP governance proxy that sits between AI clients and tool servers to apply response projection, metering, and retry policies, reducing token bloat and providing per-tool cost visibility.

FastMCP server for managing and testing webhooks via webhook-test.com API

An MCP server exposing Kubernetes-style diagnostic tools to an LLM agent, with a safety approval gate for destructive actions, all backed by a mock cluster for local testing.