Discover Awesome MCP Servers

mcpwall

mcpwall is a deterministic security proxy for MCP tool calls — iptables for MCP. It sits between the MCP client and server, intercepting every JSON-RPC request and enforcing YAML-defined policies.

mcp-server-google-cloud-logging

Claro, aquí tienes cómo obtener registros de Logging con `gcloud`: **Opción 1: Usando `gcloud logging read` (Recomendado para consultas sencillas)** Este es el método más directo para obtener registros. ```bash gcloud logging read "QUERY" --format="FORMAT" --limit=LIMIT ``` * **`QUERY`**: Es el filtro de consulta que especifica qué registros quieres. Si no proporcionas una consulta, se devolverán todos los registros (¡lo cual puede ser mucho!). Ejemplos de consultas: * `"resource.type=gke_cluster"`: Registros de clústeres GKE. * `"severity>=ERROR"`: Registros con severidad ERROR o superior. * `"textPayload:error AND logName:my-app"`: Registros que contienen la palabra "error" en el payload y provienen del log "my-app". * `timestamp>"2023-10-26T00:00:00Z" timestamp<"2023-10-27T00:00:00Z"`: Registros entre dos fechas. * Consulta la documentación de Logging para la sintaxis completa de las consultas: [https://cloud.google.com/logging/docs/view/advanced-queries](https://cloud.google.com/logging/docs/view/advanced-queries) * **`FORMAT`**: Especifica el formato de salida. Algunas opciones comunes son: * `text`: Formato legible por humanos (predeterminado). * `json`: Formato JSON. Útil para procesar los registros con otras herramientas. * `yaml`: Formato YAML. * `value(logName, timestamp, severity, textPayload)`: Formato personalizado que muestra solo los campos especificados. * Consulta la documentación de `gcloud topic formats` para más opciones. * **`LIMIT`**: El número máximo de registros a devolver. Si no se especifica, se devuelve un número limitado de registros. Usa `--limit=unlimited` para obtener todos los registros que coincidan con la consulta (¡ten cuidado con esto, puede ser mucho!). **Ejemplos:** * Obtener los últimos 10 registros de error en formato JSON: ```bash gcloud logging read "severity>=ERROR" --format="json" --limit=10 ``` * Obtener todos los registros de un clúster GKE específico en formato de texto: ```bash gcloud logging read "resource.type=gke_cluster AND resource.labels.cluster_name=YOUR_CLUSTER_NAME" --format="text" --limit=unlimited ``` * Obtener los registros que contienen "error" en el payload, mostrando solo el logName, timestamp, severity y textPayload: ```bash gcloud logging read "textPayload:error" --format="value(logName, timestamp, severity, textPayload)" ``` **Opción 2: Usando `gcloud logging tail` (Para monitoreo en tiempo real)** Esta opción muestra los registros a medida que se generan, similar a `tail -f` en Linux. ```bash gcloud logging tail "QUERY" ``` * **`QUERY`**: Igual que en `gcloud logging read`, es el filtro de consulta. Si no se especifica, se muestran todos los registros nuevos. **Ejemplo:** * Monitorear los registros de error en tiempo real: ```bash gcloud logging tail "severity>=ERROR" ``` **Consideraciones importantes:** * **Autenticación:** Asegúrate de que `gcloud` esté autenticado con una cuenta que tenga permisos para leer los registros. Puedes autenticarte con `gcloud auth login`. * **Proyecto:** Asegúrate de que `gcloud` esté configurado para el proyecto correcto. Puedes verificarlo con `gcloud config get-value project` y cambiarlo con `gcloud config set project YOUR_PROJECT_ID`. * **Cuotas:** Ten en cuenta las cuotas de Logging. La lectura excesiva de registros puede generar cargos. * **Escritura a un archivo:** Puedes redirigir la salida de `gcloud logging read` a un archivo: ```bash gcloud logging read "QUERY" --format="json" > logs.json ``` **En resumen:** * Usa `gcloud logging read` para obtener registros históricos y realizar consultas específicas. * Usa `gcloud logging tail` para monitorear los registros en tiempo real. * Asegúrate de usar consultas eficientes para evitar leer demasiados registros. * Considera el formato de salida para facilitar el procesamiento de los registros. Espero que esto te ayude. Si tienes alguna pregunta específica sobre tu caso de uso, házmelo saber y te daré un ejemplo más preciso.

ClickUp MCP Server

Securely connect AI assistants to ClickUp workspaces through OAuth 2.0, providing 72 tools across 12 categories for comprehensive task management, time tracking, project planning, and workspace operations without managing API keys.

Academic MCP

Enables AI tools to search and retrieve data from various South Korean and Japanese academic databases, including research journals, historical records, and legislative information.

Last Rock MCP

Infrastructure orchestration server for deploying and managing MCP servers on Fly.io and Cloudflare Workers with state tracking, distributed locking, health checks, and automatic rollback capabilities.

IBKR TWS MCP Server

Enables LLM clients to interact with Interactive Brokers Trader Workstation for automated trading workflows. Supports market data retrieval, portfolio management, and order execution through the TWS API.

Wuxing Search MCP

A privacy-focused search server built on SearXNG that provides unlimited, multi-source web searching across 100+ engines. It enables AI tools to perform advanced searches with specialized filters for time, language, and content categories without API costs or rate limits.

sg-data-mcp

Real-time Singapore government data for AI agents. Weather forecasts, air quality (PSI/PM2.5), HDB carpark availability, and taxi supply from data.gov.sg.

URL-Based MCP Server

URL MCP es una prueba de concepto de un constructor de servidores MCP sin estado que permite a los usuarios construir servidores MCP sin escribir ni alojar código. Está destinado a la experimentación con protocolos y seguridad, en lugar de para construir integraciones MCP del mundo real.

Advanced Obsidian MCP Server

Empowers AI agents to deeply understand and interact with Obsidian vaults through the Local REST API, enabling advanced features like vault structure discovery, graph analysis, command execution, and batch file operations.

MongoDB MCP Server by CData

MongoDB MCP Server by CData

Metabase MCP Server

Enables AI assistants to interact with Metabase analytics platform, allowing them to query databases, execute SQL, manage dashboards and cards, and access analytics data through natural language.

Fal Recraft V3 MCP Server

Provides access to the fal-ai/recraft/v3 image generation model for creating high-quality images with advanced style controls including realistic, digital illustration, and vector art styles, plus color guidance and local image download capabilities.

aster-info-mcp

An MCP server that provides structured access to Aster DEX market data—covering candlesticks, order books, trades, and funding rates.

scm-mcp

A Model Context Protocol server for managing Palo Alto Networks Strata Cloud Manager firewall configurations through natural language in Claude. It provides 149 tools covering the full configuration lifecycle including policy objects, security rules, NAT, and profiles with multi-tenant support.

freedcamp

freedcamp

Enhanced Sequential Thinking MCP Server

Enables structured problem-solving through sequential thinking stages with persistent storage and analysis. Helps break down complex problems into manageable cognitive steps while tracking progress and generating summaries of the entire thought process.

EndNote Library Reader

Enables programmatic access to EndNote .enl libraries, allowing users to list, search, and extract full text from bibliographic references and their attached PDFs through MCP tools.

Locations MCP Server

Enables WordPress content extraction, keyword research using Google autocomplete and Trends data, and generation of SEO-optimized content with quality metrics.

Ronin Defense MCP

Detects and sanitizes hidden-payload attacks in MCP communications to protect LLMs in agentic IDEs from malicious prompt injection and adversarial content delivery.

Ember MCP Server

A Model Context Protocol server that provides tooling support for Ember.js development, allowing developers to execute CLI commands, run codemods, access documentation, and discover community resources.

mcp-angular-cli

mcp-angular-cli

chuk-mcp-vfs

Provides virtual filesystem workspaces with full file operations (read, write, ls, tree, mkdir, rm, mv, cp, cd, pwd, find, grep) and checkpoint management. Supports multiple storage providers (memory, filesystem, sqlite, s3) with session, user, and shared scopes.

Country MCP Server

A modular MCP server that provides tools for looking up country and state information. Designed as a demonstration of building extensible MCP servers with custom tool modules.

GitHub DeepWiki MCP Server

This MCP server provides detailed GitHub repository information by integrating with mcp.deepwiki.com and GitHub API to fetch repository wiki content, README files, and enable intelligent question-answering about repositories.

Salesforce MCP Server

Enables natural language interactions with Salesforce data and metadata, allowing users to query records, manage custom objects, and manipulate Apex code. It provides comprehensive tools for schema exploration, aggregate queries, and field-level security management.

Nexus MCP Server

A production-ready Model Context Protocol server that brings AI-powered web search directly into development environments, providing intelligent search results with proper citations in Claude Desktop, Cursor, or any MCP-compatible client.

datadog mcp

for tracing and monitoring

Todoist MCP

Enables LLMs to interact with Todoist task management platform through its API, supporting all features from the official Todoist TypeScript Client.