Packages

HashiCorp's official MCP server for Terraform — gives agents access to the Terraform Registry to discover providers and modules, read documentation, and assist with infrastructure-as-code authoring.

Official Neon MCP server enabling AI agents to interact with Neon's serverless Postgres platform — creating and managing databases, running SQL queries, managing branches for dev/test workflows, handling connection pooling, and leveraging Neon's instant database branching for safe schema migrations.

A self-contained, serverless, zero-configuration SQL database engine embedded directly into applications. The database is a single cross-platform file. Available in Python's standard library (sqlite3 module), and via better-sqlite3 for Node.js. The most widely deployed database engine in the world, found in every browser, OS, and mobile device.

Official Algolia MCP server enabling AI agents to interact with Algolia's search platform — querying indexes, updating records, managing synonyms and rules, and analyzing search analytics.

Developer-first authentication and user management platform with prebuilt UI components, a REST API, and an MCP server for managing users, sessions, organizations, and auth flows in modern web apps.

Official CrowdStrike Falcon MCP server enabling AI agents to interact with the Falcon cybersecurity platform — querying detections, investigating incidents, searching threat intelligence, managing endpoints, hunting for threats, and integrating AI-driven security operations.

Official Tavily MCP server providing AI agents with an AI-optimized search API — returning structured, LLM-ready search results with source ranking, content extraction, and optional advanced research mode.

Open-source, typo-tolerant full-text search engine written in Rust with an official MCP server, offering instant search results, faceting, filtering, and hybrid semantic+keyword search.

Anthropic's official reference MCP server for fetching web pages and converting them to Markdown. Gives agents the ability to read any URL and get clean, LLM-friendly content.

Anthropic's Claude API enabling AI agents to call Claude models — text generation, vision, tool use, document analysis, and multi-turn conversations. The most capable Claude models including Claude 4 Opus and Sonnet.

OpenAI's official Python SDK for building multi-agent systems — provides agents, tools, handoffs, tracing, and native MCP integration with a minimal, production-ready API.

Captures, groups, and surfaces application errors and performance traces across 90+ platforms so agents can query error trends, triage issues, and trigger alerts.

Official Groq MCP server enabling AI agents to use Groq's ultra-fast LLM inference API — running completions, chat, and structured outputs with Llama, Mixtral, and other open models at industry-leading speeds for latency-sensitive agent workflows.

Official Clerk MCP server (part of Clerk's agent toolkit) enabling AI agents to manage Clerk user data — creating, reading, updating users, managing sessions, checking permissions, and handling organization memberships.

Python framework for building MCP (Model Context Protocol) servers quickly — the FastAPI equivalent for MCP, with decorators, automatic schema generation, and multi-transport support.

OpenAI's API providing AI agents access to GPT-4, GPT-4o, o1/o3 reasoning models, embeddings, vision, DALL-E image generation, Whisper speech recognition, and the Assistants API with persistent threads.

Anthropic's official reference MCP server for Git repository operations. Gives agents the ability to read git history, diffs, branches, and file contents directly from local repositories.

Serverless PostgreSQL with database branching, autoscaling to zero, and instant provisioning for development and production workloads.

Official Shopify MCP server (dev-mcp) enabling AI agents to interact with Shopify stores and developer tools — querying products, orders, customers, inventory, and accessing Shopify's development documentation.

Provides secure, long-lived cloud sandbox environments for AI agents to safely execute arbitrary code, run processes, and interact with filesystems in isolated containers.