MCP Servers

Official Supabase MCP server for database and backend integration. Enables AI agents to query PostgreSQL databases, manage tables and schemas, handle authentication users, interact with storage buckets, and invoke edge functions. Provides full access to Supabase project management including migrations and type generation.

MCP server for Firecrawl's web scraping and crawling API. Converts any website into clean, LLM-ready markdown or structured data. Supports single page scraping, multi-page crawling with depth control, sitemap-based extraction, and batch operations. Handles JavaScript-rendered pages, bypasses common anti-bot measures, and returns structured content suitable for RAG pipelines and knowledge base construction.

MCP server for Neon's serverless PostgreSQL platform. Enables AI agents to manage Neon projects, branches, databases, and roles. Supports creating database branches for development and testing, running SQL queries, managing connection strings, and performing schema migrations. Leverages Neon's instant branching for safe experimentation without affecting production data.

MCP server for Tavily's AI-optimized search engine. Designed specifically for LLM agents and RAG applications, providing concise, factual search results with source attribution. Supports general web search, news search, and direct Q&A extraction. Returns pre-processed content optimized for AI consumption with relevance scoring and content deduplication.

Official Cloudflare MCP server for managing Cloudflare services. Enables AI agents to interact with Workers, KV namespaces, R2 storage, D1 databases, and DNS records. Supports deploying Workers scripts, managing environment variables, querying analytics, and configuring security settings across Cloudflare's edge network.

Official MCP server for Qdrant vector search engine. Acts as a semantic memory layer enabling AI agents to store and retrieve information using vector similarity search. Supports storing text with metadata, semantic querying, configurable embedding models via FastEmbed, and both cloud-hosted and local Qdrant instances. Useful for building RAG pipelines, code search, knowledge bases, and long-term agent memory.