Packages

HandBrake is a free/open-source video transcoder that converts media files into formats such as MP4/MKV/MP4-compatible variants by applying codecs, containers, and encoding settings.

Provides LangChain.js adapters to integrate Model Context Protocol (MCP) tools into LangChain.js applications, supporting MCP tool usage over stdio and SSE transports via the @modelcontextprotocol/sdk dependency.

An MCP server that integrates an agent workflow with Anki via AnkiConnect (through stdio). It is intended to expose Anki/AnkiConnect operations to MCP-capable clients.

Open Multi-Agent Canvas is an open-source multi-agent chat UI built with Next.js/LangGraph/CopilotKit that lets users manage multiple agents in one conversation and connect a built-in “MCP Agent” to MCP-compatible servers (e.g., via Standard IO or SSE).

MCP server for Oracle WebLogic Server for OCI management, enabling AI agents to provision, configure, manage, and monitor Oracle WebLogic application server deployments on Oracle Cloud Infrastructure — including creating domains, managing clusters, and scaling WebLogic stacks.

PaddleSpeech is an open-source Python toolkit for building speech/audio systems. It provides training, inference, and deployment modules for tasks such as speech recognition (including streaming ASR), text-to-speech (including streaming TTS), punctuation restoration, speaker verification, keyword spotting, speech translation, audio classification, and related speech frontends (e.g., Chinese text normalization/G2P).

MCP server that exposes RhodeCode (Rhodecode/Bitbucket-compatible SCM) functionality as MCP tools so AI agents can interact with repositories/issues/changes through the MCP protocol.

Provides an MCP server that exposes “simple” MySQL connectivity as agent-callable tools (for querying/updating a MySQL database) with configuration supplied by the host environment.

MCP server package intended to expose Splatoon-related functionality (e.g., game data or queries) to AI agents via the Model Context Protocol.

Provides an MCP (Model Context Protocol) server for Spring developers, intended to expose tools that let AI assistants query information about a running Spring application (served over an SSE endpoint on localhost by default).

A template/wrapper MCP server for using AWS services from an AI agent via the Model Context Protocol (MCP). It is intended to expose AWS-related actions/tools to the agent.

An MCP server package intended to provide Zotero-related capabilities to AI agents via the Model Context Protocol, likely allowing tools to read/search/create Zotero items and metadata.

Provides an MCP (Model Context Protocol) server wrapper for Tavily, intended to be used as a Zed context server. It requires a Tavily API key for authentication and delegates retrieval/search capabilities to Tavily via the underlying Tavily MCP implementation.

An MCP server intended to help with billing cost management by exposing functions/tools (via the Model Context Protocol) related to retrieving and analyzing cost/billing information.

claude-ecom is a Claude Code skill/tool that converts an ecommerce/sales orders CSV into a structured KPI analysis (multiple time horizons, KPI decomposition, health checks) and then uses Claude to write a single consolidated REVIEW.md with prioritized findings and a concrete next-action plan.

ClickHouse Server is a high-performance columnar database system providing SQL query execution over large datasets. It offers client/server connectivity (typically via native TCP and HTTP interfaces), supports clustering/replication features, and is commonly deployed as a self-managed database service.

Provides a FastAPI example server that exposes MCP (Model Context Protocol) tool access over Server-Sent Events (SSE), alongside standard FastAPI web routes (e.g., /docs, /redoc).

k8s-mcp-server is an MCP (Model Context Protocol) server that exposes Kubernetes-related capabilities to AI agents via MCP tools, enabling agents to inspect and operate on cluster resources through a standardized interface.

Provides an MCP server implementation (based on mcp-go) that currently exposes weather-related capabilities backed by the HeFeng (和风天气) API. Includes a custom JSON unmarshal approach to transfer annotation tags into each result field's description to improve AI interpretability of responses.

MCP server that exposes Attio (CRM/contacts) functionality to an AI agent via the Model Context Protocol, enabling the agent to read/update Attio data through MCP tools.