Packages

ClawMem is a local-first context engine/memory for AI coding agents. It indexes markdown/project documents into a SQLite-based “vault”, performs hybrid retrieval (BM25 + vector + reranking + graph/intent-based traversal), and integrates with Claude Code via hooks + an MCP stdio server and with OpenClaw via a ContextEngine plugin or MCP tools. It also captures session decisions/handoffs and writes them back to the same local vault; it includes measures against prompt injection in surfaced content and supports deduplication, lifecycle (pin/snooze/archive), and crash-safe transaction-safe indexing.

Provides an MCP (Model Context Protocol) server for Membrane that exposes Membrane integration actions as MCP tools. Supports connecting over HTTP streamable transport and (deprecated) SSE, with token-based authentication and optional static vs dynamic tool exposure.

Provides a Python CLI (`kd`) and an MCP server to convert video URLs (YouTube/Bilibili/Facebook) into structured knowledge outputs by extracting subtitles when available, otherwise performing local ASR (Qwen3-ASR on Apple Silicon), and optionally generating summaries via external LLM providers (Google/OpenAI/Anthropic).

Bridges AI models (Claude, GPT, Gemini) with ROS/ROS2 robots via MCP, enabling natural language command translation into ROS commands and real-time robot state monitoring without modifying existing robot source code.

Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.

MCP server for Google Tag Manager

Provides an MCP (Model Context Protocol) server to let an MCP-capable client (e.g., Claude Desktop/Code) interact with Things 3 task-management data on macOS—listing items, searching, and creating/updating tasks and projects via Things’ URL scheme/Things.py integration. Supports stdio transport by default and optional HTTP transport via environment variables.

toolbox/sectool is a CLI + MCP server that enables collaborative application security testing between a human operator and an AI agent. It provides a wire-fidelity HTTP(S) MITM proxy (native, and optional Burp as a front-end), captures and replays authenticated browser/proxy traffic, supports crawling/diffing/reflection detection and out-of-band interaction testing (OAST via Interactsh), and exposes these capabilities as MCP tools (plus CLI commands sharing state).

VectorMCP is a Ruby gem that implements the Model Context Protocol (MCP) server-side specification, providing a framework to register MCP tools, resources, prompts, and filesystem roots, and to run the server over transports such as stdio or SSE/HTTP.

Cloud invoicing and accounting software API for freelancers and small businesses. Strong focus on time tracking, project-based billing, invoicing, and expense management.

Free and premium REST API for real-time and historical stock prices, forex rates, cryptocurrency data, and technical indicators, widely used for financial analysis and trading applications.

MCP server that enables AI assistants to search, download, and analyze academic papers from arXiv, with local caching and specialized research analysis prompts.

astro-airflow-mcp is a Model Context Protocol (MCP) server (FastMCP-based) that exposes Apache Airflow functionality (via Airflow’s REST API) to AI agents. It can run standalone over MCP (stdio/HTTP) or as an Airflow 3.x plugin, and supports multiple Airflow auth styles (bearer token, basic auth, and username/password with OAuth2 token exchange for Airflow 3.x).

ComfyUI-AnimaTool provides tool interfaces (MCP server, ComfyUI-compatible HTTP routes, and an optional FastAPI server/CLI) that let an AI agent generate Anima anime/illustration images via a running ComfyUI instance. It supports structured prompts, aspect ratio presets, history/reroll, and batch generation (repeat and batch_size), and includes optional LoRA injection behavior.

drf-mcp-docs exposes Django REST Framework API documentation to AI coding agents via the Model Context Protocol (MCP). It provides MCP resources and tools to browse endpoints/schemas/auth methods and to generate frontend/client integration code snippets, using DRF schema generators (drf-spectacular, drf-yasg, or DRF built-in).

Provides an MCP (Model Context Protocol) server (Python) that integrates with Notion’s API to let MCP clients list/query databases, create/update pages, search a Notion workspace, and fetch database details and block children.

opencode-mcp is an MCP server that bridges MCP clients (via stdio) to the OpenCode headless API over HTTP. It auto-starts an OpenCode server when needed and exposes 79 tools, 10 resources, and 6 prompts for delegating coding, debugging, and project/session operations.

OpenTabs turns browser tabs (and existing authenticated browser sessions) into an agent-accessible tool system. It exposes actions via MCP tools, and supports a plugin system that discovers/registers site APIs for in-browser calls, plus built-in browser tools (e.g., screenshots/clicking/typing/network capture).

railway-mcp is an unofficial community MCP (Model Context Protocol) server that lets MCP clients manage Railway.app infrastructure—projects, environments, services, deployments, variables, networks, and (partially) databases—via MCP tools using a Railway API token for authentication.

Provides an MCP server for Claude Code that persists “infinite memory” across sessions by saving conversation chunks and extracting/saving reusable “insights”. It auto-snapshots before Claude Code’s /compact and supports search (regex, BM25, optional semantic embeddings), retention/archiving, and multi-project organization.