Packages

Provides an MCP server (CLI) that allows an agent to access Qonto’s Business API endpoints that are available via Qonto API key authentication.

A MCP server package intended to help agents perform real-time web scraping tasks (fetching and extracting data from web pages) via Model Context Protocol tools.

Scira MCP Chat is a Next.js-based web UI chatbot that connects to Model Context Protocol (MCP) servers. It supports HTTP and SSE transports for MCP tool access and integrates with multiple LLM providers via Vercel's AI SDK, offering streaming responses and a settings UI for adding/enabling MCP servers.

Provides an MCP (Model Context Protocol) server that connects an agent to Elasticsearch to perform common Elasticsearch operations (e.g., querying and indexing/search-related actions) through MCP tools.

A Model Context Protocol (MCP) server intended to expose ROS (Robot Operating System) capabilities through tools that connect to a ROS bridge via WebSocket, enabling AI assistants to monitor and publish ROS topics.

Provides an MCP server that creates TinyURL short links using the TinyURL API, configured via an API key in environment variables.

Provides an MCP server (in Rust) that integrates with the Apple Music API to let clients search for songs and generate deep links for songs or playlists, using Apple Developer/Apple Music API credentials provided via CLI.

eureka-server is a server-side component for Netflix Eureka, providing service discovery for microservices by registering service instances and allowing clients to query instance metadata for locating and load-balancing requests.

Gearlynx is a cross-platform Atari Lynx emulator with a built-in debugger and an embedded MCP server (stdio or HTTP) intended to support AI-assisted debugging and tooling. It also supports a libretro core.

A Streamlit-based LangChain MCP client web app that lets users connect to MCP (Model Context Protocol) servers for tool access and chat with multiple LLM providers (OpenAI, Anthropic, Google Gemini, and local Ollama). It includes streaming responses, multimodal/file attachments, multi-server tool integration, and session/persistent memory backed by LangGraph (in-memory + SQLite).

Open-source enterprise AI agent platform that combines RAG (retrieval-augmented generation) with agentic workflows and MCP tool-use support. Enables document upload, web crawling, automatic text segmentation and vectorization, and zero-code integration into existing business systems for intelligent Q&A. Supports multiple LLM backends including DeepSeek, Llama, Qwen, OpenAI, Claude, and Gemini.

MCP (Model Context Protocol) server for Windows that enables remote/programmatic control of a desktop: mouse movement/clicks, keyboard input/shortcuts, window management, screen capture, and clipboard operations, exposed via MCP SSE transport.

mcp-crash-course is an educational repository that teaches the Model Context Protocol (MCP) via a set of hands-on project topics organized in git branches (e.g., SSE, LangChain adapters, Docker containerization, and MCP prompts). It is not presented as a production API/service; it provides learning materials and sample implementations around MCP.

Provides multiple Model Context Protocol (MCP) server implementations that wrap common security testing tools (e.g., SQLMap, Nmap, FFUF, Nuclei, Masscan, etc.) so they can be invoked via a standardized MCP interface, including a Docker image approach for deployment.

An MCP (Model Context Protocol) server that connects to an Oracle database and exposes a large set of tools for database/schema/user/table management, analytics and performance diagnostics (e.g., AWR/ADDM/DBMS_STATS), and (optionally) Oracle 23c vector search and AI-assisted content/query operations. It also supports a REST mode for testing alongside the default stdio MCP transport.

Provides an MCP server that connects an agent to Google BigQuery so the agent can perform BigQuery operations (e.g., query execution and related data access) via MCP tool calls. The package name indicates BigQuery-specific MCP functionality.

Provides a Go-based MongoDB-backed server that exposes gRPC operations for managing models, contexts, executing protocols, tracking protocol execution status, and storing/retrieving arbitrary data. It also mentions an MCP-style (Model Context Protocol) and Cursor IDE integration via a /mcp prefix.

NDepend.MCP.Server is an MCP (Model Context Protocol) server package intended to expose NDepend functionality to AI agents via MCP tools/handlers so agents can query and work with .NET code analysis results.

MCP server for Oracle OCI Zero Trust Packet Routing (ZPR), enabling AI agents to manage security policies that control packet routing at the network layer using zero-trust principles on Oracle Cloud Infrastructure — defining which workloads can communicate with each other based on identity rather than IP addresses.

python-ai-kit is a project template/boilerplate for generating production-oriented Python applications for AI agents (including multi-agent orchestration and state), MCP servers, and FastAPI-based microservice/monolith APIs. It emphasizes observability, testing/evaluation pipelines, prompt versioning, and (in template features) security practices like encrypting API keys.