MCPs tagged with # llm-integration

Druid MCP Server provides a fully MCP-compliant interface for managing, analyzing, and interacting with Apache Druid clusters. Leveraging tools, resources, and AI-assisted prompts, it enables LLM clients and AI agents to perform operations such as time series analysis, statistical exploration, and data management through standardized protocols. The server is built with a feature-based architecture, offers real-time communication via multiple transports, and includes automatic discovery and registration of MCP components.

• ⭐ 9
• MCP
• iunera/druid-mcp-server

SQLite Explorer MCP Server provides a safe, read-only interface to SQLite databases using the Model Context Protocol (MCP). Built with the FastMCP framework, it enables large language models to explore, query, and retrieve database schema information with robust safety and validation mechanisms. The server exposes structured tools such as read_query, list_tables, and describe_table, ensuring secure and reliable access to database contents. Designed for integration with platforms like Claude Desktop and Cline VSCode Plugin.

• ⭐ 93
• MCP
• hannesrudolph/sqlite-explorer-fastmcp-mcp-server

MongoDB Lens offers a local Model Context Protocol (MCP) server that enables full-featured interaction with MongoDB databases using natural language queries through large language models. It provides tools for querying, running aggregations, schema analysis, performance optimization, and more. The server supports integration with a variety of MCP clients, making MongoDB data accessible and manageable by natural language commands. Users benefit from features such as connection aliasing, schema inference, and data protection mechanisms for sensitive operations.

• ⭐ 191
• MCP
• furey/mongodb-lens

Provides a Model Context Protocol-compliant server offering read-only access to MySQL databases, enabling LLMs to inspect schemas and execute SELECT queries. Enforces strict SQL validation to allow only read-only operations and exposes table schema information in JSON format. Communication occurs over JSON-RPC via stdio to ensure compatibility with LLM systems. Features simple configuration, automatic schema discovery, and robust security measures.

• ⭐ 11
• MCP
• dave-wind/mysql-mcp-server

Chroma MCP Server implements the Model Context Protocol to allow seamless integration between LLM applications and external data using the Chroma embedding database. It enables AI models to create, manage, and query collections with advanced vector search, full text search, and metadata filtering. The server supports both ephemeral and persistent client types, along with integration for HTTP and cloud-based Chroma instances. Multiple embedding functions, collection management tools, and rich document operations are available for extensible LLM workflows.

• ⭐ 418
• MCP
• chroma-core/chroma-mcp

CentralMind Gateway automatically generates secure, LLM-optimized APIs for structured databases and exposes them via REST, OpenAPI 3.1, or the Model Context Protocol (MCP), including Server-Sent Events (SSE) for AI agents. It integrates privacy protection, auditing, and authentication mechanisms to enable seamless and compliant data access for AI-powered applications. The tool supports multiple database backends and is optimized for AI workloads, providing enhanced metadata for improved context understanding.

• ⭐ 500
• MCP
• centralmind/gateway

iMessage MCP offers a Model Context Protocol (MCP) server that facilitates seamless integration between large language models (LLMs) and macOS iMessage data. It provides robust tools for searching and managing iMessage messages, conversations, and contacts in a read-only manner. Features include message and contact search, chat listing, and context retrieval, making it suitable for conversational agents and context-aware applications. Built using Deno and designed for easy integration with applications such as Claude Desktop, it handles context management efficiently for AI models.

• ⭐ 16
• MCP
• wyattjoh/imessage-mcp

MCP Notify Server provides system desktop notifications and sound alerts when AI agent tasks or LLM jobs finish. Built on the standard Model Context Protocol, it is cross-platform and designed for smooth integration with clients like Claude Desktop, Cursor, and VSCode. This tool leverages the Apprise API for notification delivery and includes configuration details for easy adoption across popular AI/LLM development environments.

• ⭐ 39
• MCP
• Cactusinhand/mcp_server_notify

CLI MCP Server provides a secure implementation of the Model Context Protocol (MCP) for executing command-line operations with robust security features. It enables controlled CLI access by enforcing command and flag whitelisting, path validation, and shell operator restrictions, making it suitable for integration with large language model applications. Designed for configurable deployment, it supports detailed error reporting, execution timeouts, and strict working directory controls.

• ⭐ 155
• MCP
• MladenSU/cli-mcp-server

Serena is a free and open-source coding agent toolkit that enhances large language models with advanced semantic code retrieval and editing tools. It enables integration through the Model Context Protocol (MCP), allowing seamless operation with various coding agents, IDEs, and interfaces. Serena extracts code entities at the symbol level, supports context-aware operations, and improves token efficiency for coding tasks. The tools can be incorporated into diverse LLM-driven environments for more efficient and precise code editing.

• ⭐ 15,643
• MCP
• oraios/serena

code-to-tree is an MCP (Model Context Protocol) server that enables large language models to accurately convert source code into abstract syntax trees (AST) across multiple programming languages. It provides a standalone executable that integrates with MCP clients, ensuring seamless parsing using the tree-sitter framework. The server supports languages including C, C++, Rust, Ruby, Go, Java, and Python, with minimal dependencies required. Its design focuses on ease of setup and integration in AI workflows requiring code analysis capabilities.

• ⭐ 66
• MCP
• micl2e2/code-to-tree

Winx Agent is a Rust implementation of WCGW, offering advanced shell execution and file management for large language model code agents. It delivers high-performance, multi-provider AI integration, including automatic fallbacks and code analysis capabilities. Designed for seamless integration with Claude and other LLMs, it leverages the Model Context Protocol (MCP) for standardized context handling. Multiple operational modes, advanced file operations, and interactive shell support make it suitable for robust AI-driven code workflows.

• ⭐ 21
• MCP
• gabrielmaialva33/winx-code-agent

MCP Nutanix is an experimental Model Context Protocol (MCP) server that allows large language models to interact with Nutanix Prism Central APIs. It facilitates listing and accessing resources such as VMs, clusters, and hosts via standardized MCP client-server integration, using the Prism Go Client for backend communication. The implementation supports both interactive and static credential methods, making it compatible with various MCP clients including Claude and Cursor.

• ⭐ 11
• MCP
• thunderboltsid/mcp-nutanix

Apple Health MCP Server enables users to import, parse, and analyze Apple Health data exports, seamlessly connecting them to large language models (LLMs) that support the Model Context Protocol. Built on the high-performance FastMCP framework, it supports natural language querying, trend analysis, and integration with databases like Elasticsearch, ClickHouse, and DuckDB. The project offers modular tools for data exploration, structure analysis, and automated statistics generation. Designed for flexibility and scalability, it is container-ready and provides extensive configuration options.

• ⭐ 64
• MCP
• the-momentum/apple-health-mcp-server

MKP is a Model Context Protocol (MCP) server designed for Kubernetes environments, allowing large language model (LLM) powered applications to list, retrieve, and apply Kubernetes resources through a standardized protocol interface. Built natively in Go, it utilizes Kubernetes API machinery to provide direct, type-safe, and reliable operations without dependencies on CLI tools. MKP offers a minimalist, pluggable design enabling universal resource support, including custom resource definitions, and includes built-in rate limiting for production readiness.

• ⭐ 54
• MCP
• StacklokLabs/mkp