An MCP server that runs right inside the IDE, for connecting to MySQL, Postgres, SQLite, and MSSQL databases.

Lightning-fast, privacy-first research platform with local data processing, multi-LLM support, web search, and knowledge graph generation.

An MCP server that securely interfaces with your iMessage database via the Model Context Protocol (MCP), allowing LLMs to query and analyze iMessage conversations. It includes robust phone number validation, attachment processing, contact management, group chat handling, and full support for sending and receiving messages.

Kotlin multiplatform toolkit for building context-enabled LLM integrations with transports and coroutine-friendly APIs across JVM, JS, native, and Wasm.

Intelligent task orchestration with persistent memory, auto-decomposition, and context-preserving workflows for developers.

Open-source agent OS enabling multi-agent collaboration, tool use, and human-in-the-loop workflows for scalable AI experiments.

Transforms GraphQL into a fast, schema-aware router with single-command setup and federation compatibility.

AI-powered Markdown formatting with direct WeChat drafts publishing, in-chat styling, and theme-driven layouts.

Direct Kagi search integration with an extensible MCP framework, optimized for Claude Desktop, featuring private beta API access and a clear upgrade path.

Connects large language models to ROS-enabled robots, enabling bidirectional control and real-time observation without modifying existing robot code.

Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.

Natural language interface enabling AI assistants to diagnose, deploy, and optimize Kubernetes with 253 tools and rich dashboards.

Hybrid RAG powerhouse that blends graph, vector, and full-text search with MCP-enabled agents for scalable knowledge graphs and context engineering.

Official dbt integration enabling AI agents to access Core metadata, semantic layer queries, and discovery APIs for enhanced data modeling workflows.

Lightweight wrapper converting MCP tools to LangChain tools with multi-server access for LangChain and LangGraph workflows.

Official CoinGecko TypeScript API integration enabling AI assistants to explore endpoints, test requests, and leverage structured documentation.

Delivers precise, token-efficient documentation context for APIs and libraries, with session-aware filtering and dual setup options for HTTP stream or local stdio.

DuckDuckGo-powered search backend with content extraction, rate limiting, and LLM-friendly result formatting.

Renders JavaScript-heavy pages with Playwright, extracts main content, and outputs Markdown or HTML, featuring parallel fetch, resource blocking, and robust error handling.

Unified data access across Harness with 11 tools and 163 resources, enabling multi-project automation and zero-config setup.

A fine-tuned PPT generation engine delivering high-quality slides through editing-based workflow and rich tool integrations.

A lightweight MCP server that allows LLMs to read and interact with your personal PDF and EPUB ebooks. Ideal for building AI reading assistants or chat-based ebook interfaces.

Self-hosted GaiaNet node enables private, decentralized AI agents with local models, vector search, and Web3-ready workflows for offline, secure experimentation.

Run more than +200 onchain actions on any blockchain including Ethereum, Solana and Base.