Packages

Puppeteer MCP server enabling AI agents to control headless Chrome for browser automation — navigating web pages, taking screenshots, filling forms, extracting page content, executing JavaScript, and integrating Puppeteer's browser automation capabilities into agent-driven web scraping, testing, and web interaction workflows.

Redis Stack extends Redis with JSON document storage (RedisJSON), full-text and vector search (RediSearch), time-series data (RedisTimeSeries), and probabilistic data structures. Builds on Redis's in-memory key-value store with sub-millisecond latency. Accessible via the Redis protocol (RESP) using standard Redis clients, plus a REST API via Redis Stack Server. Available as Redis OSS + Stack modules, or Redis Cloud.

Official Shortcut MCP server enabling AI agents to interact with Shortcut (formerly Clubhouse) project management — creating, reading, and updating stories and epics, managing workflows and iterations, searching for stories, accessing member and team data, and integrating Shortcut project management into agent-driven sprint planning and engineering workflow automation.

An MCP server that provides LLMs with up-to-date, version-specific documentation and code examples for programming libraries. Resolves library names to Context7 IDs, then retrieves current documentation and examples directly into the agent's context. Prevents hallucinated or outdated API references by pulling from live sources.

Draw.io MCP server enabling AI agents to create and manipulate Draw.io (diagrams.net) diagram files — generating architecture diagrams, flowcharts, network diagrams, and entity-relationship diagrams; reading existing diagrams; and integrating Draw.io's diagram creation into agent-driven documentation and visualization workflows.

HubSpot MCP server enabling AI agents to interact with HubSpot's CRM and marketing platform — managing contacts, companies, deals, and tickets; querying engagement history; automating sales workflows; sending emails; and integrating HubSpot CRM data into agent-driven sales and marketing automation.

Neo4j MCP server enabling AI agents to interact with Neo4j graph databases — executing Cypher queries, managing graph schemas and constraints, performing graph analytics with Neo4j Graph Data Science (GDS), accessing knowledge graphs, and integrating Neo4j's powerful graph database capabilities into agent-driven knowledge management and graph analytics workflows.

Official Notion MCP server giving AI agents access to Notion workspaces for reading and writing pages, databases, blocks, and comments.

Office PowerPoint MCP server enabling AI agents to create and manipulate Microsoft PowerPoint presentations (.pptx files) — adding slides with text, images, charts, and shapes; applying themes; reading presentation content; and integrating PowerPoint generation into agent-driven presentation creation and reporting workflows.

Official Postman MCP server from Postmanlabs enabling AI agents to interact with Postman — reading and executing Postman collections, managing APIs and environments, running API tests, querying collection structures, and integrating Postman's API development and testing platform into agent-driven API testing, documentation, and development workflows.

Headless CMS with a real-time content lake, GROQ query language, and MCP server, supporting highly customizable content models with live collaboration.

Open-source cloud browser infrastructure built specifically for AI agents. Provides managed Chromium sessions accessible via Playwright, Puppeteer, or CDP. Features session management, anti-detection, CAPTCHA solving, and file handling. Can be self-hosted or used as a hosted service. Direct open-source competitor to Browserbase.

Official Apify MCP server enabling AI agents to run Apify Actors — a marketplace of 2,000+ pre-built web scraping and automation tools for Google Search, Amazon, social media, and many other platforms.

Official Atlassian MCP server providing unified access to Jira, Confluence, and Bitbucket — enabling AI agents to search, read, and interact with Atlassian's suite of developer and project management tools.

Official Neo4j MCP server from neo4j-contrib enabling AI agents to interact with Neo4j graph databases and Neo4j Aura — executing Cypher queries, managing graph data, exploring schema, querying knowledge graphs, and integrating Neo4j's graph capabilities into agent-driven data workflows for graph analytics and relationship-based reasoning.

The world's most advanced open source relational database, providing ACID-compliant transactional storage with rich SQL support, JSONB, full-text search, geospatial (PostGIS), and extensive extension ecosystem. Accessed via SQL drivers (libpq, psycopg2, asyncpg, node-postgres).

Todoist MCP server enabling AI agents to interact with Todoist's task management app — creating and updating tasks, managing projects and sections, querying task lists and due dates, handling labels and filters, and integrating Todoist's personal productivity system into agent-driven task automation workflows.

Tree-sitter MCP server enabling AI agents to parse and analyze code using Tree-sitter's language-aware parser — generating syntax trees from source code, querying specific code constructs, extracting function and class definitions, and integrating structured code analysis into agent-driven code review and refactoring workflows across 40+ programming languages.

Official MCP server from dbt Labs that bridges AI agents with dbt projects. Provides tools for SQL execution, natural language to SQL conversion, semantic layer querying, project discovery (models, macros, sources, lineage), CLI operations (build, test, compile), dbt Cloud admin API access, and YAML/SQL code generation for dbt models.

Unified data and AI platform REST API — manage clusters, notebooks, jobs, ML experiments, SQL warehouses, and Unity Catalog data assets programmatically.