Packages

A Model Context Protocol (MCP) server implementation that provides access to [NebulaGraph](https://github.com/vesoft-inc/nebula).

An MCP server that provides full text search for code declarations. Uses SQLite with FTS5 and universal ctags to index and search functions, classes, structures, enums, and other code elements. Supports all languages that ctags supports including Python, C, Go, C++, JavaScript, Rust, Java, and many others.

[](https://archestra.ai/mcp-catalog/rae-api-com__rae-mcp)

Agent skills for [SpriteCook](https://spritecook.ai) - AI-powered game asset generation. These skills teach AI coding agents how to generate pixel art and detailed/HD game art including sprites, characters, items, tilesets, and more using SpriteCook's MCP tools.

这是一个基于 `Model Context Protocol (MCP)` 的TuShare数据服务器，提供了一系列股票市场数据查询接口。

A Python MCP server that generates diagrams (UML via PlantUML and others via Kroki/related renderers) from natural language and/or provided diagram code, exposing tools and resources through MCP and an HTTP endpoint (including a FastAPI app with `/mcp` for hosted use).

MCP server for creating Whimsical diagrams

This extension integrates [GitHub MCP Server](https://github.com/github/github-mcp-server) as a context server for

This extension integrates [Sequential Thinking](https://github.com/modelcontextprotocol/servers/tree/main/src/sequentialthinking)

A production-ready integration platform that gives AI agents secure access to 14+ real-world services (GitHub, Slack, Airtable, HubSpot, Notion, Spotify, Stripe, etc.) through a unified MCP server and REST API. Handles OAuth flows and credential management via HashiCorp Vault so agents don't need to deal with auth complexity directly.

AgentRunKit is a lightweight Swift 6 framework for building LLM-powered agents with type-safe tool calling, streaming, context management/compaction, structured outputs, multimodal support, and an MCP client (stdio/JSON-RPC). It supports both cloud providers (e.g., OpenAI-compatible, Anthropic, Gemini, Vertex) and on-device inference via MLX and Apple Foundation Models.

Provides an MCP server that enables AI agents to query SAP Cloud Integration (Integration Suite) tenant data—such as integration packages, flows, mappings, and runtime artifacts—by calling SAP CPI public OAuth-protected APIs using the client-credentials flow.

A Model Context Protocol (MCP) server that lets MCP-compatible clients (e.g., Claude Desktop) interact with Discord via a JSON-RPC 2.0 interface over stdio. It supports Discord bot operations such as sending and retrieving messages, getting channel info, searching messages, and moderation actions, with configurable YAML + environment overrides and options for JWT/API-key authentication.

Provides an MCP server (and local HTTP endpoint) that lets AI assistants query and manipulate ERPNext/Frappe data using generic “doctype” tools, plus wrapper project analytics tools. It can connect to ERPNext via Frappe/ERPNext APIs and to an OpenAI-compatible LLM provider (including local Ollama).

Provides an MCP server (via a Docker image) that exposes the official Godot Engine documentation to AI assistants, including a documentation tree and retrieval of specific files such as class docs and tutorials.

Provides an MCP server plus CLI to fetch and return structured data derived from Google News RSS feeds (by keyword/location/topic/top news) and Google Trends (trending keywords by geo). Optionally summarizes/condenses articles using LLM/NLP pipelines.

Open-source testing framework supporting API testing (HTTP/WebSocket/RPC), vision-driven UI automation (Android/iOS/browser via OCR/CV), and load testing. Includes MCP server for AI-assisted test orchestration and an interactive chat mode.

Kubernetes kube-apiserver is the core Kubernetes control-plane API server that exposes the Kubernetes REST API, performs authentication/authorization, validates requests, and coordinates persistence and admission of cluster state changes.

Android RPA framework providing 160+ APIs for device automation, remote desktop with WebSocket streaming, UI inspection, Frida integration for dynamic analysis, and MCP server for AI agent tool-calling. Supports Android 6-16 on physical devices, emulators, and cloud phones.

lc2mcp is a Python adapter that converts existing LangChain tools (e.g., @tool functions, StructuredTool, BaseTool-derived tools) into FastMCP-compatible tools, registering them on a FastMCP server with optional context injection, docstring/args-schema handling, and namespace/collision management.