Packages

A comprehensive MCP server providing AI agent access to the full Google Workspace suite: Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Chat, Tasks, Contacts, and Apps Script. Supports OAuth 2.0/2.1, multi-user auth, read-only mode, tool tier filtering, and both HTTP and stdio transports.

Google Lighthouse MCP server enabling AI agents to run web performance and quality audits using Lighthouse — analyzing pages for performance scores, Core Web Vitals, accessibility issues, SEO problems, and best practices. Enables AI agents to audit web pages and provide actionable improvement recommendations for web developers and performance engineers.

Go-based MCP server for managing and serving reusable prompt templates by smallnest — a prolific Go developer. Enables AI agents to load, query, and use stored prompt templates — supporting prompt engineering workflows, prompt versioning, and systematic prompt management for AI development teams.

Official Microsoft Sentinel MCP server enabling AI agents to explore security data, query logs with KQL, investigate incidents, and perform threat hunting in Microsoft Sentinel SIEM.

MCP server that converts natural language questions into SQL queries against any PostgreSQL database, returning results in table, JSON, or CSV format with streaming support for large result sets.

Official StarRocks MCP server enabling AI agents to interact with StarRocks — the high-performance analytical SQL database — executing queries, exploring table schemas, analyzing data, and integrating StarRocks's fast OLAP capabilities into agent-driven data analytics and business intelligence workflows.

tmux MCP server enabling AI agents to control tmux terminal multiplexer sessions — creating and managing windows and panes, sending commands to terminal sessions, reading terminal output, and integrating tmux's persistent terminal management into agent-driven shell automation and multi-process orchestration workflows.

Official collection of MCP servers from AWS Labs providing AI agents access to AWS services. Includes servers for AWS documentation lookup, infrastructure-as-code (CloudFormation, CDK, Terraform), container orchestration (EKS, ECS), serverless (SAM CLI, Lambda), cloud resource management (Cloud Control API), and AWS Support. Enables foundation models to read AWS docs, manage infrastructure, and automate cloud operations.

Python framework for orchestrating role-playing AI agents that collaborate on complex tasks — agents are assigned roles, goals, and tools, then work together as a 'crew'.

Official CrewAI Enterprise MCP server enabling AI agents to deploy and interact with CrewAI's enterprise multi-agent orchestration platform — managing crews, agents, and tasks; kicking off multi-agent workflows; retrieving execution results; and integrating CrewAI's collaborative agent framework into other MCP-based agent workflows.

Intentionally vulnerable MCP server for security education — modeled after DVWA (Damn Vulnerable Web Application), it exposes common MCP security vulnerabilities including prompt injection, tool poisoning, excessive permissions, and authentication flaws, enabling security researchers and developers to learn MCP attack/defense patterns in a safe environment.

Official Grafana Loki MCP server enabling AI agents to query logs stored in Loki using LogQL — searching log streams, filtering by labels, running log metric queries, and analyzing log data for incident investigation.

Kibana MCP server enabling AI agents to interact with Kibana — the Elastic stack's visualization and observability platform. Enables querying Elasticsearch through Kibana's APIs, reading dashboards and saved searches, running KQL (Kibana Query Language) queries, accessing log and metric data, and integrating observability data into agent workflows for incident response and data analysis.

MCP server that gives Claude Desktop (and other MCP clients) direct access to relational databases via SQLAlchemy. Provides tools for schema exploration, table relationship visualization, SQL query execution, and large dataset handling with optional file export via claude-local-files.

Official Microsoft Clarity MCP server enabling AI agents to interact with Microsoft Clarity UX analytics — querying session recordings, heatmap data, user behavior metrics, page performance insights, and integrating Clarity's behavioral analytics into agent-driven UX optimization and web performance analysis workflows.

MCP server for xc — the Markdown-based task runner that defines tasks in README.md files. Enables AI agents to discover and run xc tasks defined in a project's Markdown files, list available tasks, and integrate xc-based project workflows into agent-driven development. Xc is a popular tool that makes tasks self-documenting by embedding them directly in project README files.

A lightweight, universal MCP server for safe Obsidian vault access. Provides 14 tools for note CRUD, batch reading, BM25 search, frontmatter management, tag operations, and vault statistics. Works across Claude, ChatGPT, and any MCP-compatible AI assistant with strong YAML frontmatter safety.

Official MCP server for the Resend email platform, enabling AI agents to send emails, manage contacts, handle broadcasts, and administer domains through MCP clients.

Official Microsoft Azure MCP server providing AI agents with access to Azure resources: storage accounts, Cosmos DB, App Config, and more — with Azure CLI-compatible authentication.

MCP server for Doppler — the universal secrets manager for developer teams and CI/CD. Enables AI agents to manage secrets, sync configurations across environments, rotate secrets, and audit access logs. Doppler eliminates .env files by providing a central platform for secrets management across development, staging, and production.