"MCP servers that can be triggered by uvx or npx" matching MCP servers:

MCP servers for real-time development monitoring and interactive pair programming.

Provides tools for DeepTempo AI SOC including findings and case management, investigation workflow orchestration, action approval workflows, and MITRE ATT&CK layer generation.

Provides MCP servers for managing Huawei Cloud ECS, CodeArts Pipeline, and CTS audit logs with unified JWT authentication and role-based access control.

Provides a scalable, containerized infrastructure for deploying and managing Model Context Protocol servers with monitoring, high availability, and secure configurations.

Enables natural language Kubernetes operations, including smart resource queries, pod root-cause analysis, cross-environment diffs, and manifest generation.

An MCP server that enables interaction with Google Cloud Logging API, allowing users to write, read, and manage log entries and configurations through natural language.

Relays error logs from other MCP servers when an LLM call fails and the returned error message is unclear, helping the model handle errors more intelligently.

The policy enforcement plane for MCP: deterministic admission and egress policy, attributable audit, and SIEM export for your MCP server fleet. Self-hosted and MIT licensed.

MCP server for managing Ubuntu servers over SSH. Enables Claude to check system health, inspect services, tail logs, review updates, and run commands remotely.

TrustPilot for APIs, built for AI agents. Independent reliability ratings for APIs and MCP servers — look up trust scores, compare providers side by side, and leave reviews from real agent traffic.

Shows what is consuming your agent context window before a session starts: always-loaded skill descriptions ranked by token cost, skills installed more than once under different names, CLAUDE.md/AGENTS.md sizes including what their @import lines pull in, and MCP servers configured across clients. Read-only: no child processes, no network.

MCP server that exposes Avangenio's service status by fetching and parsing status.avangenio.com/data.txt into normalized JSON.

A read-only MCP server for Proxmox VE that provides AI assistants with structured visibility into cluster nodes, guests, storage, and Docker workloads. It is designed to prevent any mutating operations by construction.

An MCP server for Grafana Loki that enables LLMs to query, tail, and analyze logs, featuring fuzzy container-name matching, compact output, and tools for log patterns, volume, and label discovery. It can run as a local stdio server or a containerized HTTP service.

Read-only MCP server that exposes Grafana dashboards, datasources, and metric/log queries as tools, for use by skills in the TICKETS workspace.

MCP server for inspecting IBM Liberty/WebSphere application servers over SSH, enabling reading sanitized configs, performing health checks, and searching logs remotely.

A Python MCP server that reduces token usage by ~98% when working with log files by auto-detecting format and stripping noise to return only actionable signal.

Streams live progress from long-running MCP tool calls to any connected client. Instrument a tool call with mcp-telemetry-sdk, and telemetry_subscribe pushes its steps, logs, cost, and completion over notifications/progress — no polling, and a job started in one session can be watched from a different one.

An MCP server for Microsoft Defender Advanced Hunting that enables AI assistants to investigate security events using natural language by translating queries to KQL and executing them against Defender.

An MCP server that enables AI agents to safely operate multi-cluster Kubernetes fleets through an Open Cluster Management hub, with policy enforcement, human approval, and audit tracing.