MCP App StoreMCP App Store
from Aqua (agent messaging CLI)253
CLI-first messaging and inbox tool for agents — send/receive messages, manage contacts, watch inboxes, and integrate webhook wakeups for agent workflows.
Aqua provides a CLI-centric transport and local mailbox for AI agents. It lets agents send and receive peer-to-peer messages, manage contacts and invites, monitor inboxes for unread messages, and run a persistent aqua serve process (optionally with a webhook) to wake agents on new traffic. Use it to build reliable agent inbox workflows and to integrate external wakeup paths into agent runtimes.
Use Aqua when agents need lightweight, CLI-driven peer messaging, reliable inbox semantics, or an HTTP webhook wakeup path. Good for agent-to-agent communication, inbox-driven automation (poll or watch), relay-backed P2P connections across NATs, and supervised daemon patterns where a runtime prefers webhook callbacks.
serve, inbox watch/list, contacts invite/accept, send, and webhook-driven integration.Primarily CLI-friendly agent runtimes and platforms that can supervise background processes or consume JSON CLI output (agent-friendly JSON mode). Works well with agent frameworks that can call shell tools or supervise daemons (e.g., Copilot/Codex/CLI-based agents, agent runners that support webhook wakeups).
Aqua Communication is a CLI-first P2P messaging tool for AI agents using libp2p. The SKILL.md is comprehensive with clear quick-start guides for relay and direct modes, group operations, and troubleshooting tables. The install script downloads and attempts to install the aqua binary from GitHub releases but failed in DRY_RUN due to needing sudo for /usr/local/bin. The SKILL.md instructs users to use a curl|bash install pattern which is a significant security concern.
The curl|bash install pattern in the SKILL.md is the main security concern. The install.sh script itself is well-written with proper error handling, temp dir cleanup, and OS/arch detection. No signs of malicious intent — just standard install convenience patterns that happen to be risky. The skill is genuinely useful for agent-to-agent communication.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
AWP (Agent Work Protocol)
Tooling and scripts for onboarding, staking, allocation, and managing agents on the AWP network (Base/Ethereum/Arbitrum/BSC). Includes safe, opt-in daemon and r
BluOS CLI (blu)
Control Bluesound and NAD speakers: discover devices, play/stop, group/ungroup, and set volume from the CLI.
OpenDAL Oli CLI Playbooks
Command playbooks and safe-operation patterns for the OpenDAL 'oli' CLI — listing, copying, moving, editing, and benchmarking data across local and remote profi
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Markdrop
Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.