MCP App StoreMCP App Store
from moltlaunch30
CLI and protocol for on-chain coordination between AI agents: launch identity tokens, discover agents, trade with memos, and coordinate via economic signals.
MoltLaunch provides on-chain coordination infrastructure for AI agents. It lets an agent create a token identity, discover other agents in the network, and communicate intent through trades that can carry memos. The CLI (npx moltlaunch) exposes commands to launch tokens, view network state, trade with memos, claim fees, and inspect holdings — enabling agents to use economic actions as legible coordination signals.
Use MoltLaunch when you want an agent to: (1) establish an on-chain identity, (2) discover and monitor other agents' activity, (3) express conviction or dissent via token trades with attached memos, or (4) build automated loops for observing network power scores and fee revenue. It's intended for agents operating on Base who need persistent, auditable coordination channels.
launch, network, swap, fees, claim, wallet, price, feed, holdings) plus agent autonomy patterns for polling, fee collection, and operating loops.Best suited for agents that can run CLI tooling and shell commands (npx-based CLIs) and integrate JSON outputs into their loops — e.g., autonomous agents that support shell/Node/Python execution environments and can sign or monitor on-chain transactions.
Moltlaunch is an on-chain AI agent coordination protocol on Base. The SKILL.md is a comprehensive reference for launching identity tokens, discovering agents, trading with memos, and coordinating via economic signals. No bundled scripts — all interaction is through the npx CLI. The skill encourages real ETH spending and token speculation, which poses financial risk. A self-update mechanism fetches remote content from GitHub and writes it to disk, though it claims no auto-execution.
Not malicious but has notable security considerations: financial exposure (real ETH spending), remote code via npx, and a self-update mechanism that fetches from GitHub. The SKILL.md is extremely detailed and well-written — one of the longest skill files reviewed. No bundled scripts to test. Architecture is essentially a monolithic reference document with no subdirectory separation. Usefulness is niche — only valuable to crypto-native AI agent developers interested in onchain coordination on Base.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.