Packages

Provides an MCP server (TypeScript/Node via @salesforce/mcp) that lets an MCP client/LLM securely interact with Salesforce orgs using a configurable set of DX/MCP tools (e.g., orgs, metadata, data, users, DevOps Center, etc.).

mcp-handler is a Vercel/Next.js (and Nuxt) adapter that lets you expose Model Context Protocol (MCP) servers over web transports such as Streamable HTTP and Server-Sent Events (SSE). It provides a createMcpHandler wrapper to register MCP tools with input schemas and handler functions, then exports Next.js route handlers for GET/POST.

Provides an MCP (Model Context Protocol) server that controls a Teenage Engineering EP-133 K.O. II sampler via MIDI, exposing commands for connecting to MIDI ports, playing notes and drum patterns, and browsing the device’s sound/pad mappings.

Provides an MCP (Model Context Protocol) server implemented with Spring Boot (Java 21) that exposes user-management tools (e.g., get/search/add/update/delete users). It supports synchronous communication and multiple transports (STDIO and an HTTP/SSE-style /mcp/message endpoint). Tool calls appear to act as a thin wrapper over an external DummyJSON API for user data.

Provides an MCP (Model Context Protocol) server for retrieving MOEX stock quotes and related market/financial news, with tools for stock search, gainers/losers, today’s news, keyword search, and news by ticker. Supports caching (Redis or in-memory) and optional storage of historical data in MongoDB, and exposes predefined MCP tools and prompt templates for LLMs.

MIE (Memory Intelligence Engine) is a local/persistent memory layer for AI agents. It exposes an MCP server with tools to store, query, update, delete, export, and repair a typed knowledge graph (facts/decisions/entities/events/topics) backed by an embedded graph database (CozoDB) and optional local embeddings (e.g., via Ollama).

nano-agent is an MCP server that exposes a small set of file-system tools to agent clients, and provides a CLI for running agent workflows across multiple LLM providers (OpenAI, Anthropic, and local Ollama models). It is designed to support “nested” agent execution (MCP client/outer agent calls a single MCP tool, which orchestrates internal agent/tool usage).

pwno-mcp runs GDB (with pwndbg) inside an isolated environment and exposes stateful debugging/exploit I/O workflows to LLM agents via an MCP server, with support for multiple sessions and helper automation.

Provides a read-only MCP (Model Context Protocol) server that exposes SFTP data via CData JDBC Driver (JDBC models) to MCP-capable clients (e.g., Claude Desktop). It supports listing tables/columns and running SQL SELECT queries through MCP tool calls (stdio-based, same-machine clients).

SkillBoss Skills is a skills/MCP-enabled integration layer for AI coding agents, providing access to 100+ AI services (chat LLMs, image/video generation, TTS, etc.) via a unified API key. It includes a CLI, an MCP server package for MCP-compatible clients (e.g., Claude Code/Cursor/Windsurf/Cline), and skill pack documentation for agent platforms, plus related deployment/workflow integrations (e.g., Cloudflare Workers, D1/KV/R2 provisioning, Stripe payments, scraping/search, email sending).

StreamNative MCP server that implements an MCP server interface for AI agents to manage and use StreamNative Cloud resources plus Apache Kafka and Apache Pulsar (admin and client operations). It supports both stdio and SSE transport modes and can connect to StreamNative Cloud using service-account authentication or to external Kafka/Pulsar clusters directly.

Provides an MCP context server integration for Zed to access Linear (issues, projects, etc.) using either an extension setting (linear_api_key) or the official Linear MCP server endpoint (mcp.linear.app) with a Bearer token header.

Adeu is a Python DOCX redlining engine and MCP server that helps AI agents apply “Track Changes” edits to Microsoft Word documents by calculating diffs and injecting native Word XML (w:ins/w:del) and comments without breaking existing formatting/layout.

Provides four example integration patterns for accessing Kalshi prediction market data with AI agents: an MCP server wrapper around a CLI, a standalone CLI with JSON/Human output and local caching, progressive-disclosure file-system scripts, and a Claude Code “skill” that reuses those scripts with team sharing via git.

An AI-assisted patent drafting and analysis system for Claude Code that combines (1) an MCP server exposing tools for MPEP/USC/CFR regulation search via hybrid RAG, (2) large-scale patent search via Google BigQuery (public patent datasets) plus optional USPTO API checks, (3) automated 35 USC 112(a)/(b) and formalities-style reviews, and (4) diagram generation using Graphviz.

dedalus-mcp (Dedalus MCP) is a Python framework for building MCP (Model Context Protocol) clients and servers. It provides ergonomic decorators and registration for MCP tools, resources, prompts, and related capabilities, plus streamable HTTP and stdio transports and support for protected servers (e.g., DPoP) as described in the README.

Entroly is a context engineering/optimization tool for AI coding agents. It ingests and indexes a workspace, scores/selects and compresses codebase context to fit within token budgets, and delivers that optimized context to agents via an MCP server or a local HTTP proxy. It also provides a dashboard/metrics, explain endpoints, and optional reinforcement-learning-style weight adjustment from feedback.

An MCP server that connects to a user’s Gmail account (via Google OAuth) and exposes tools to send emails, read emails (and mark them as read), list unread emails, mark an email as read, move an email to trash, and open an email in a browser.

A Model Context Protocol (MCP) server that exposes a recipe/diet assistant backed by the HowToCook dataset, offering tools to query recipes, filter by categories, fetch recipe details, recommend a weekly menu based on constraints (e.g., allergies/avoid items/people count), and generate a menu for today.

MCP server for integrating with Shopify e-commerce platform, enabling Model Context Protocol clients to interact with Shopify stores and APIs