Packages

Anthropic's official 'everything' MCP server — a comprehensive test server that implements every MCP feature (tools, prompts, resources, sampling) for testing MCP clients and agent integrations.

Anthropic's Claude LLM API providing text, vision, and tool-use capabilities across Claude 3.5 Sonnet, Claude 3 Opus, and Haiku model variants with up to 200K token context.

Anthropic's official reference MCP server for local filesystem access. Gives agents read/write access to files and directories on the host machine, with configurable path restrictions.

Stripe Billing is the subscription and invoicing layer of the Stripe platform, providing APIs for managing Products, Prices, Subscriptions, Invoices, and Customer billing portals. Used by SaaS companies to automate recurring revenue, proration, metered usage billing, and dunning workflows.

The developer's payment platform with APIs for accepting payments, managing subscriptions, handling billing, and fraud prevention, with an official MCP server.

Official GitHub MCP server enabling AI agents to interact with GitHub repositories, issues, pull requests, code search, Actions workflows, and more — built by GitHub.

GitHub REST API v3 — programmatic access to repositories, issues, pull requests, Actions workflows, code search, and the full GitHub platform, enabling agents to automate code review, issue triage, CI/CD workflows, and repository management.

GitHub's REST API for managing Actions workflows — trigger runs, check status, download artifacts, manage secrets, and control runner infrastructure programmatically from agents.

GitHub's official MCP server — gives AI agents direct access to GitHub repositories, issues, pull requests, code search, and Actions via the Model Context Protocol.

Anthropic's official reference MCP server for persistent agent memory using a local knowledge graph. Agents can create entities, relations, and observations that persist across sessions.

Embedded in-process OLAP database optimized for analytics — reads Parquet, CSV, and JSON files directly with full SQL support, running inside Python, Node, or any language without a server.

Official Resend MCP server enabling AI agents to send transactional emails via Resend's developer-first email API — composing and sending emails with HTML/text content, managing contacts, and handling email delivery.

Stripe's document identity verification service that confirms real user identities by collecting government IDs and selfies, returning structured verification results via the Stripe API.

Neon is a serverless PostgreSQL platform that separates compute from storage to enable instant database branching, scale-to-zero, and autoscaling. Each Neon branch is a full copy-on-write snapshot of the database, enabling safe schema migrations, isolated test environments, and per-PR previews with zero additional storage cost until data diverges. The Management REST API controls infrastructure: creating projects, branches, compute endpoints, roles, and connection strings. The HTTP SQL API executes Postgres queries over HTTPS without a persistent TCP connection. The official Neon MCP server (25+ tools) gives AI agents direct control over the full Neon platform — running SQL, managing migrations on temporary branches, analyzing slow queries, and provisioning databases — making Neon one of the most agent-ready databases available.

Anthropic's official reference MCP server for web search via the Brave Search API. Gives agents real-time web search results without sending queries to Google.

Anthropic's official reference MCP server for SQLite databases. Gives agents full read-write SQL access to local SQLite database files, including schema inspection and query execution.

Stripe's official MCP server (part of the Stripe Agent Toolkit) giving agents the ability to create payment links, manage customers, handle subscriptions, retrieve transaction data, and automate billing workflows.

GitHub's official MCP server that gives AI agents full access to GitHub's platform: repositories, issues, pull requests, Actions workflows, code security findings, Dependabot alerts, discussions, and notifications. Available as a hosted remote server or self-hosted Docker container.

Firecrawl converts any URL or website into clean, LLM-ready markdown. It handles JavaScript-rendered pages, bypasses common anti-scraping measures, converts PDFs and other formats, and returns structured content that agents can immediately use without HTML parsing. Includes crawl (multi-page), scrape (single-page), extract (structured data with schema), and search endpoints.

Official Cloudflare MCP server enabling AI agents to interact with Cloudflare's platform — managing Workers, KV storage, D1 databases, R2 buckets, DNS records, firewall rules, and other Cloudflare services.