Packages

Turso MCP server enabling AI agents to interact with Turso's edge SQLite platform — managing libSQL databases, executing queries, creating and managing database groups, and leveraging Turso's globally distributed SQLite for edge-native applications.

Centralized coordinator that manages multiple MCP servers and exposes all their capabilities through a single unified MCP endpoint.

Official AWS sample MCP servers from aws-samples organization demonstrating how to build MCP servers for AWS services — including samples for Amazon Bedrock, EC2, S3, IAM, CloudWatch, and other AWS services, providing reference implementations for AWS-native AI agent development and showing AWS service integration patterns for MCP.

MCP server that gives AI assistants access to Apple's official developer documentation. Searches across 50+ frameworks (SwiftUI, UIKit, Foundation), 1260+ WWDC video transcripts, code examples, and platform compatibility info. Runs via npx with 35MB of bundled WWDC data for offline access.

Financial Modeling Prep (FMP) MCP server enabling AI agents to access comprehensive financial data — stock prices, financial statements (income statement, balance sheet, cash flow), financial ratios, earnings data, company profiles, insider transactions, and macroeconomic indicators from FMP's financial data API. Enables agents to perform financial analysis and research.

Official MiniMax MCP server that gives AI assistants access to MiniMax's generative media APIs including text-to-speech, voice cloning, image generation, video generation (Hailuo-02), and music creation. Outputs are saved locally or to a configurable path.

Community MCP server for MongoDB — enabling AI agents to query, insert, update, and delete documents, manage collections and indexes, run aggregation pipelines, and inspect database schemas in MongoDB or MongoDB Atlas.

Alph is a Universal MCP Server Configuration Manager that simplifies the configuration of various AI agents by automating the setup process and ensuring error-free configurations.

MCP server for Azure OpenAI Service — Microsoft's enterprise deployment of OpenAI models (GPT-4, GPT-4o, GPT-4 Turbo, Whisper, DALL-E) with enhanced compliance, private networking, and data processing guarantees. Enables AI agents to call Azure-hosted OpenAI models with EU/US data residency, private endpoints, and Microsoft's enterprise SLA.

BigQuery MCP server enabling AI agents to interact with Google BigQuery — executing SQL queries against petabyte-scale datasets, listing datasets and tables, exploring schema, running analytical queries, and integrating BigQuery's serverless data warehouse capabilities into agent-driven analytics and data pipeline workflows.

Blender Open MCP server enabling AI agents to interact with Blender — the professional open-source 3D creation suite — creating and modifying 3D objects, controlling materials and lighting, managing scene hierarchies, and integrating AI-driven 3D modeling and scene creation into agent workflows for animation, visualization, and game asset creation.

MCP server for Cal.com — the open-source Calendly alternative. Enables AI agents to manage scheduling via Cal.com — creating bookings, checking availability, managing event types, and interacting with the Cal.com scheduling platform. Both self-hosted and Cal.com Cloud supported.

Claude Historian MCP server enabling AI agents to search and retrieve past Claude conversation history — indexing and querying previous Claude chat conversations, finding relevant past discussions, and surfacing historical context to enhance current agent sessions with persistent conversation memory.

ClickHouse is a blazing-fast open-source columnar OLAP database designed for real-time analytics over massive datasets. It stores data in column-oriented format with aggressive compression, enabling queries that scan billions of rows per second. ClickHouse accepts SQL via an HTTP interface (port 8123/8443) and a native binary protocol (port 9440), with support for many input/output formats (JSON, CSV, Parquet, Arrow). ClickHouse Cloud is the managed offering with a REST Management API for programmatic cluster management. The HTTP interface supports streaming responses, progress headers, and session-based queries — making it well-suited for agents that need to run complex analytical queries.

Delphi MCP Server is a native implementation of the Model Context Protocol (MCP) designed for AI-powered Delphi development workflows, supporting both HTTP and STDIO transport modes.

MCP server providing dynamic shell command execution capabilities to AI agents. Enables agents to run shell commands, scripts, and system operations with configurable permissions and command filtering — providing a controlled interface to shell execution rather than unrestricted terminal access.

A local MCP server for accessing the EVE Online ESI API, providing multi-character support and automatic token management.

MCP server providing Haskell language tooling to AI agents — enabling agents to evaluate Haskell expressions, type-check code, run GHCi REPL sessions, compile Haskell modules, and get type information. Integrates Haskell's powerful type system and functional programming capabilities into AI-assisted development workflows.

Kilntainers is an MCP server that provides isolated Linux sandboxes for executing shell commands by LLM agents.

Linear MCP server (streamable variant) enabling AI agents to interact with Linear's engineering project management platform — creating and managing issues, updating project status, querying teams and cycles, and integrating Linear's developer-focused PM tool into agent-driven engineering workflow automation.