Packages

Provides an npm-installed Node/TypeScript CLI + long-running daemon that manages MCP servers and exposes “progressive disclosure” layers (metadata/status → tool list → per-tool schema) to help agents call MCP tools with less context/token usage. Uses a Socket (newline-delimited JSON) between CLI and daemon, which then connects to MCP servers via MCP transports (e.g., stdio).

AllVoiceLab-MCP is an MCP server that exposes tools for text-to-speech, voice conversion, voice cloning, video translation/dubbing, subtitles extraction, and subtitle removal by calling AllVoiceLab’s underlying TTS/VC/video translation APIs.

google-slides-mcp is an MCP (Model Context Protocol) server that provides tool functions to interact with the Google Slides API, enabling an agent to create presentations, fetch presentation/slide data, perform batch updates to modify slides, and summarize slide text content.

An MCP (Model Context Protocol) server that exposes Hacker News data as callable tools. It provides tools to fetch news lists (top/new/best), fetch story details with comments, fetch user profiles/recent activity, and search Hacker News via the Algolia API; it includes input validation with zod and HTTP calls via axios.

IronCurtain is a TypeScript runtime/CLI for autonomous AI agents that enforces a human-readable “constitution” (policy) compiled into deterministic rules. It mediates all agent tool calls via MCP servers (e.g., filesystem/git/github/workspace) and a policy engine that allows/denies/escalates actions for user approval, with agent code isolated in a V8 sandbox (builtin mode) or an external agent constrained by Docker + network/MCP mediation (docker mode).

llm is a Python library and command-line tool for interacting with large language models (both via remote APIs like OpenAI/Anthropic/Gemini and via locally installed/self-hosted models through plugins). It supports running prompts from the CLI, managing API keys, chat, embeddings, structured extraction (schemas), tool execution, and logging to SQLite.

A lightweight Flask API bridge that connects Claude Desktop (or any MCP-compatible client) to a Kali Linux machine, enabling AI-assisted command execution for authorized penetration testing and CTF challenges. The server exposes a thin HTTP API on port 5000 that accepts arbitrary shell commands and returns their output, effectively giving an AI assistant a live Kali terminal. Tools like Nmap, Metasploit, sqlmap, Gobuster, enum4linux, and any other Kali tool are accessible by name. The architecture is intentionally minimal — a single Flask server with no auth, no sandboxing, and no command filtering — making it fast to set up for isolated testing environments but completely unsuitable for production or shared infrastructure.

A Spring Boot–based MCP (Model Context Protocol) server that exposes a tool to query local computer/system configuration (OS info, hardware details, current user info, and Java runtime version), intended to run via stdio in an MCP client.

Provides a Go-based CLI tool and an MCP server for writing notes to Flomo, with support for Markdown content and comma-separated tags. Configuration is done via an environment variable pointing at a Flomo API/endpoint URL.

Provides a Python MCP (Model Context Protocol) server with coding-plan specific tools, including web search and image understanding, intended to be used by MCP-compatible coding assistants via stdio (local) or SSE (network/cloud) transports.

OWL is an open-source Python multi-agent framework built on top of CAMEL-AI to orchestrate collaborative agent workflows for real-world task automation. It supports tool use across many domains (e.g., online search, browser automation via Playwright, document parsing, multimodal analysis, code execution) and integrates Model Context Protocol (MCP) tool calling plus additional toolkits (including MCP toolkits, file/terminal capabilities, and various domain-specific toolkits).

Provides an MCP server with multiple tools for searching and analyzing US patent data using the free USPTO PatentsView API (e.g., search, patent details, citations, technology trends, CPC/IPC classification search, families, claim extraction, top holders, portfolio comparison, and landscape/strategic analysis).

pine-mcp-server is a local MCP server (Python) that exposes tools for managing Pine AI assistant sessions and task execution. It supports authentication via Pine access token/user id or via an email-based code flow, and provides MCP tools for creating/listing/getting/deleting sessions, sending conversation messages/forms/location responses, starting/stopping tasks, uploading/deleting attachments, and handling call reminders/social sharing.

reprompt-cli (re:prompt) is a local-first CLI tool to scan and analyze prompts generated in AI coding tools. It provides a prompt dashboard, prompt scoring (research-calibrated), conversation distillation/compression, privacy checks for sensitive content exposure, and optional integrations such as a browser extension and an MCP server for certain tools. It claims analysis runs locally with no LLM calls/network requests for the scoring flows.

The microsoft/skills repository provides a curated catalog of “agent skills” (copy/installable templates) and related assets (custom agents/AGENTS.md templates and MCP configurations) aimed at AI coding agents working with Azure SDKs and Microsoft AI Foundry. It includes a “skills.sh” installer/wizard, plus a “mcp-builder” skill to help create MCP servers for LLM tool integration.

Provides a local, read-only Model Context Protocol (MCP) server that exposes Snapchat Ads data to AI clients by wrapping a CData JDBC Driver connection as MCP tools (get tables, get columns, run SELECT queries).

Provides a Spring Boot implementation of an MCP (Model Context Protocol) server exposing crypto/news-related tools (search/get latest news, token tracking, sentiment analysis) over HTTP (JSON-RPC) and SSE transports, with SQLite persistence and Caffeine caching.

Trae Agent (trae-cli) is a Python CLI framework for LLM-based, general-purpose software engineering tasks. It runs an agent loop with a configurable tool ecosystem (e.g., file editing and bash execution), supports multiple LLM providers, can record detailed trajectories for debugging, and optionally integrates MCP servers for additional tool/model context.

TUUI is a desktop “local AI playground” client built around the Model Context Protocol (MCP). It can connect to different LLM backends (including hosted APIs) and manage MCP servers to provide tools/prompts/resources and related MCP client features. It also supports discovery/registry and (via configuration) running local or remote MCP servers (e.g., Cloudflare mcp-remote).

zeromcp is a minimal, zero-dependency (stdlib-only) Python implementation of the Model Context Protocol (MCP) that lets you expose typed Python functions as MCP tools/resources/prompts, and serve them over HTTP/SSE or over stdio.