Packages

Agentic framework that automatically generates complete PowerPoint presentations from documents, research topics, or freeform prompts, with reflective design capabilities and text-to-image asset generation.

Provides a local, read-only MCP server that exposes Sage 200 data via CData’s JDBC Driver. It wraps the JDBC driver and exposes MCP tools to list tables/columns and run SQL SELECT queries (JSON-RPC tool calls) for use by local MCP-capable clients (e.g., Claude Desktop).

SimpleMem is a Python memory framework for LLM agents that stores, compresses (semantic lossless compression), and retrieves long-term memories using semantic/lexical/symbolic indexing. It supports cross-session/persistent memory and can be used via MCP (cloud-hosted and/or run locally with Docker) and via Python integration with OpenAI-compatible LLM/embedding backends.

An MCP server that exposes Oracle Cloud Infrastructure (OCI) Notifications service APIs, enabling AI agents to create and manage pub/sub topics, configure subscriptions (email, HTTPS, Slack, PagerDuty, SMS, OCI Functions), and publish messages to notification channels for event-driven workflows.

An MCP (Model Context Protocol) server that connects a client (e.g., Claude Desktop) to Anki via the AnkiConnect plugin, exposing Anki decks and note models as MCP resources and providing tools to list/create notes.

A tutorial/demo Model Context Protocol (MCP) server for Cursor that exposes a few custom tools (code architecture/planning, screenshot-related help, and code review from git diffs). It is run via stdio and uses local environment configuration plus OpenAI and browser automation (puppeteer).

Mastodon is a decentralized social networking platform (ActivityPub) that provides a server to host federated microblogging (posts, timelines, profiles, follows, likes/reblogs, etc.). The package refers to the Mastodon software/app used to run a Mastodon instance or integrate with its APIs.

Provides an MCP server that generates and edits PowerPoint (.pptx) presentations via MCP tools (create presentation, add slide types like title/content, tables, charts, and picture slides). It can also generate images using a Stable Diffusion WebUI (ForgeUI/Automatic1111) and save both images and the final deck to a configured folder.

A Python MCP server that provides a shared cache for AI-agent computed results, including a trust/verification mechanism where agents can store results, confirm accuracy, and retrieve only entries that meet a configurable minimum trust threshold. Cache entries expire via TTL and basic/advanced analytics tools are exposed via MCP tools.

Provides an MCP server that allows an AI agent to control a Chrome browser instance and perform web-browsing actions (open browser/tabs, navigate, click links, input text, extract page text, take screenshots, manage cookies).

An MCP server that enables AI agents to publish content, search posts, retrieve recommendations, manage comments, and access user profiles on Xiaohongshu (小红书/RedNote) via headless browser automation.

A self-hosted MCP (Model Context Protocol) server that provides tools to run AI test suites (unit/integration/performance/security/quality) and evaluate model outputs using various metrics. It is configured to use external model providers (e.g., OpenAI/Anthropic) via environment variables and exposes MCP tool definitions such as run_test_suite, evaluate_output, and generate_test_cases.

Provides an MCP server that exposes ArcticDB functionality as structured tools for AI assistants, enabling read/write operations on libraries, symbols, metadata, snapshots, batch operations, and query helpers via MCP (stdio by default, HTTP/SSE optional).

Provides an MCP (Model Context Protocol) server for integrating AI tools with GitHub, enabling agents to read repository/code context, manage issues and pull requests, analyze code/security findings, and automate GitHub workflow-related tasks. Supports both a remote hosted MCP endpoint and a locally run server (Docker/Go binary/stdio/http modes).

holoviz-mcp is an MCP server (Model Context Protocol) plus related “agent skills” that helps AI agents and humans access the HoloViz ecosystem. It provides documentation search, metadata/introspection for Panel/hvPlot components (and related tooling), and a display server capability for serving Panel visualizations via shareable URLs. The README notes the display/server side may execute Python code for serving Panel apps, with configuration and a referenced security consideration page.

ILSpy MCP Server is a Model Context Protocol (MCP) server that lets an AI assistant decompile and analyze .NET assemblies using ILSpy. It supports operations such as decompiling assemblies/types/members, listing and searching types, and analyzing type relationships/hierarchies, intended to be used by MCP-compatible clients.

json-server is a utility that turns a local JSON file into a mock REST API (CRUD endpoints) with optional support for common REST patterns like filtering, sorting, pagination, and custom routes.

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.