Packages

Twilio's cloud-based transactional and marketing email delivery API, used by agents and applications to send reliable, tracked emails at scale with dynamic templates and suppression management.

MCP server for generating UML diagrams programmatically, typically using PlantUML or similar tools. Enables AI agents to create UML diagrams from text descriptions — class diagrams, sequence diagrams, activity diagrams, component diagrams — and render them as images for documentation and architecture visualization.

Windows CLI MCP server enabling AI agents to execute commands in Windows Command Prompt and PowerShell — running CMD scripts, executing PowerShell commands, managing Windows system operations, and integrating Windows command-line capabilities into agent-driven Windows automation and development workflows.

High-performance MCP server for Obsidian providing AI tools with direct vault access through semantic operations, graph navigation, fuzzy text matching, Dataview query execution, and HTTP transport for network-based integration.

MCP server that exposes Chrome DevTools Protocol (CDP) capabilities to AI agents, enabling agents to attach to Chrome browser sessions, inspect DOM elements, capture network traffic, execute JavaScript in page context, take screenshots, and perform debugging operations through structured MCP tool calls.

An MCP server that enables AI assistants to discover and use Claude Agent Skills through semantic search with vector embeddings, bridging Anthropic's Skills framework to any MCP-compatible application.

Discord MCP server enabling AI agents to interact with Discord — reading and sending messages in channels, managing server members, creating and managing roles, posting to channels, and integrating Discord's community platform into agent-driven community management, notification, and automated moderation workflows.

MCP server wrapping Google's Gemini AI API. Enables AI agents to call Gemini models for text generation, multimodal analysis (text + images + video), code generation, and reasoning tasks. Provides a standardized MCP interface to Gemini's capabilities including Gemini Pro, Ultra, and Flash model variants.

MCP server that bridges Language Server Protocol (LSP) servers (gopls, rust-analyzer, pyright, etc.) to AI clients, giving LLMs semantic code navigation — go-to-definition, find references, diagnostics, hover docs, and rename symbol — instead of naive text search.

MCP Sandbox enabling AI agents to execute code in isolated sandboxed environments — running Python and other code safely in Docker containers, capturing output, preventing filesystem and network access, and integrating safe code execution into agent-driven development and data analysis workflows without local system risk.

MCP server providing AI agents with access to Storybook — the component development environment used by most frontend teams. Enables agents to browse component stories, read component documentation, inspect component props and variants, and reference design system components when generating or reviewing UI code.

DINO-X MCP server from IDEA Research enabling AI agents to perform universal object detection and visual grounding — detecting any objects in images using open-vocabulary detection, grounding object descriptions to bounding boxes, and integrating DINO-X's state-of-the-art vision capabilities into agent-driven image analysis workflows.

Debug Adapter Protocol (DAP) MCP server enabling AI agents to control debuggers via the Debug Adapter Protocol — setting breakpoints, stepping through code, inspecting variables, evaluating expressions in debug context, and integrating AI-assisted debugging into development workflows. Supports any DAP-compatible debugger (VS Code debug adapters, gdb, lldb, etc.).

MCP server from Descope (descope-sample-apps org) for their authentication and user identity platform. Enables AI agents to manage users, handle authentication flows, query audit logs, and interact with Descope's identity management capabilities — supporting AI-driven user management and security monitoring workflows.

Community MCP server for Elasticsearch enabling AI agents to perform full-text searches, manage indices, query documents, and analyze data stored in Elasticsearch clusters.

Flutter MCP server enabling AI agents to interact with Flutter mobile and cross-platform app development — querying widget trees, accessing Flutter DevTools data, running Flutter commands, managing project structure, and integrating Flutter's cross-platform development toolkit into agent-driven mobile app development workflows.

GDB MCP server enabling AI agents to interact with GDB (GNU Debugger) — setting breakpoints, stepping through code execution, inspecting memory and registers, analyzing stack frames, evaluating expressions, and integrating AI-driven debugging assistance into C/C++ and native code debugging workflows for bug hunting and program analysis.

MCP server for Keycloak — the leading open-source Identity and Access Management (IAM) platform — enabling AI agents to manage Keycloak realms, users, roles, clients, and authentication flows. Allows agents to automate identity management tasks: creating users, assigning roles, configuring OAuth clients, managing realm settings, and querying authentication policies.

A TypeScript proxy that exposes stdio-based MCP servers over Streamable HTTP and Server-Sent Events (SSE) — enabling remote HTTP access to local MCP servers, with support for stateful and stateless modes, API key authentication, CORS, SSL/TLS, and public tunneling via pipenet.

MCP server enabling AI agents to interact with Visual Studio Code — opening files, navigating the editor, running commands, reading diagnostics, and controlling VS Code's interface programmatically. Bridges the gap between AI agents and the VS Code editor for automated development workflows, code navigation, and editor-level automation.