"Kit" matching MCP servers:

A TypeScript MCP server starter kit supporting stdio and HTTP/SSE transports. Includes tools for system metrics, HTTP fetching with URL restrictions, and temporary key-value memory with namespace and TTL support.

Provides a deployable template that turns a Cloudflare Workers account into a hosted MCP endpoint with OAuth-gated private tools, auto-generated docs, health checks, rate limiting, and a server-rendered monitoring dashboard.

Enables AI assistants to query company logs, databases, caches, and config centers (e.g., Aliyun SLS, MySQL, Redis, Nacos) through local MCP servers, with read-only enforcement and SSH tunneling for production access.

Exposes homelab and IT-ops tools to Claude, including system health monitoring, Grafana alert states, Docker container status, Loki logs, SMART disk health, and more.

Asynchronous MCP server for unified multi-platform network infrastructure management, providing 97 tools across 10 connectors including SSH, MikroTik, Palo Alto, Aruba, Graylog, LibreNMS, Cisco APIC/NDFC, and Panorama.

An MCP server for Prometheus-based monitoring that enables users to query system metrics, resource usage, and PostgreSQL health across multiple environments. It supports both predefined diagnostic checks and custom PromQL execution for comprehensive server monitoring and troubleshooting.

Reduces log files to remove noise and duplicate information, cutting tokens by 70-90% for AI agents, preserving only errors, warnings, and unique events.

Enables auditing coding-agent claims against local execution traces to detect contradictions, exposing session audits, recent failures, and optional scope-alignment triage.

Enables AI agents and software engineers to investigate and resolve realistic distributed-system incidents using safe MCP-based diagnostic tools for code, logs, metrics, traces, database, and deployments.

A defensive MCP server for Claude Desktop / any MCP client — the blue-team counterpart to offensive tooling. 123 tools + 4 resources across Wazuh SIEM, multi-provider threat intelligence, MITRE-driven 3-Sum APT correlation, attack graphing, LangGraph investigation workflows, and host forensics. Read-only by default.

Enables agents to traverse a FalkorDB service graph by reading topology and open incidents, running graph algorithms, and executing multi-hop root-cause investigations whose LOCATE, SUGGEST and PROPOSE stages persist as resumable traces. It also surfaces episodic memories and searches runbooks and ownership records, while keeping raw Cypher, tenant switching, approvals and simulation out of reach.

ocal LLM proxy with semantic cache — Aho-Corasick normalization (1114 rules), metrics dashboard.

A local gateway that caches LLM prompts and tool results, stores searchable compressed context, and relays downstream MCP tools under deny-by-default rules. It keeps everything in one SQLite database with a single ledger tracking tokens paid upstream versus tokens avoided, plus a web console for live metrics.

Enables AI clients to perform safe, read-only IT diagnostics and retrieve local runbooks, asset records, and knowledge articles through MCP, with allowlisted network checks and audit logging.