Packages

Plan Cascade is an AI-assisted, multi-stage software development framework that decomposes a project goal into a mega plan, per-feature PRDs/design docs, parallel stories/tasks, and “quality gates” (verification, lint/format, test checks, and review). It supports multiple execution modes including a Claude Code plugin, a CLI, and a desktop app, and includes an MCP server component (FastMCP) plus an MCP client/client-side integration for tools.

The package provides an MCP (Model Context Protocol) server that exposes Gmail-related actions/tools to AI agents, enabling programmatic access to a user’s Gmail for tasks like reading and managing email.

MCP (Model Context Protocol) server package intended to provide “scholar”/academic research capabilities to an MCP-capable agent. Provides a programmatic interface for research-oriented tools (exact endpoints/tools not provided in the prompt content).

Evaluates source artifacts for security issues via an MCP (Model Context Protocol) server interface, intended to be used by AI agents to run or orchestrate scanning workflows.

Provides an MCP server that connects to a Temporal server to expose Temporal workflow history via an MCP tool (workflow_history) and a documentation-like MCP resource (test://resource).

time-server-mcp is an MCP (Model Context Protocol) server package intended to provide time-related capabilities to AI agents/tools.

Provides a local Model Context Protocol (MCP) server exposing WordNet-based lexical lookup functions such as synonyms, antonyms, hypernyms/hyponyms, and word definitions/examples.

A Kotlin Multiplatform sample project that displays Galway bus information with map visualization, built with Jetpack Compose for Android and SwiftUI for iOS/macOS. Serves primarily as a KMP learning reference with a bundled MCP server.

An experimental MCP server (localhost-only) that exposes k0rdent management capabilities—such as managing ClusterDeployments, installing/deleting ServiceTemplates, listing providers/credentials, and Kubernetes read operations like namespaces/events/pod logs—to MCP-compatible AI clients.

An MCP (Model Context Protocol) server that runs user-provided code inside isolated, resource-limited sandbox environments using runc/OCI containers. It supports multiple programming languages via language-specific handlers and offers persistence for sandbox state via SQLite. It can expose MCP over stdio or HTTP/WebSocket and includes configurable security policies and audit logging.

Provides a Model Context Protocol (MCP) server implemented in Rust (Axum, Shuttle) with an OAuth 2.1/Auth0-based authentication flow. It exposes MCP JSON-RPC 2.0 endpoints (public initialize/handshake, protected tools/resources/prompts) and includes built-in tools/resources/prompts plus a registry-based architecture for extending capabilities.

mkinf is a Python SDK/utility for integrating MCP-style “hub” agents/tools into applications via a unified interface (e.g., pulling tools from mkinf hub and wiring them into LangChain chains/graphs). It requires a hub account and an API key for accessing hub functionality.

Provides an MCP server that enables an AI agent to interact with a MongoDB instance (e.g., inspect databases/collections and run MongoDB operations) via the Model Context Protocol.

Provides an MCP (Model Context Protocol) server for working with PDBe (Protein Data Bank in Europe) related resources, exposing PDBe functionality to MCP-capable agents/tools.

Provides an MCP server exposing “questions” functionality to MCP-compatible AI agents (e.g., for retrieving, answering, or searching question-like content).

ragflow-mcp-server-continue is an MCP server integration intended to let an AI agent interact with RagFlow (RAG) capabilities so the agent can use RagFlow-backed retrieval/workflows from within an MCP-compatible client.

A MCP server that exposes Sekora-backed OpenSearch capabilities to AI agents via the Model Context Protocol, allowing the agent to run searches and related operations against an OpenSearch index using MCP tool calls.

An MCP server that integrates Snyk functionality into an agent workflow via the Model Context Protocol, enabling agents to perform Snyk-related security/vulnerability queries and actions through MCP tools.

An MCP server that connects AI agents (via MCP clients like Claude/Claude Desktop/OpenAI Codex) to Tendem for AI-assisted task management, using a Tendem API key.

tuya-mcp-server is an MCP server that bridges an MCP-capable agent to Tuya/Smart-home style device control and data access (e.g., discovery and interacting with Tuya devices) using the Tuya integration backend it wraps.