#on-chain

A lightweight, high-performance Model Context Protocol (MCP) server for the Base L2 network. This server equips AI coding agents (such as Cursor, Windsurf, Zed, or Claude Desktop) with a powerful EVM toolset.

Backtesting Arena

Schoasch

Quantitative crypto backtesting & Bitcoin-cycle analytics. DSR-corrected, point-in-time, look-ahead-aware — proprietary, not from public APIs. Free tier.

MCP server for Polymarket whale tracking and smart-money analytics. Filtered leaderboard (airdrop-farmers excluded), hedge detection, NegRisk correction, and unique Ukraine territorial markets with ISW frontline overlay. 5 tools, 4 prompts, 3 resources.

Swiss Whale Intelligence

alpineflow-io

**Swiss Whale Intelligence MCP** — 45 on-chain analytics tools for **Bitcoin, Ethereum, Solana, USDT (ETH + Tron), and tokenized gold (XAUT + PAXG)**, exposed via Model Context Protocol with anonymous OAuth 2.1 (Free tier, no signup required to install).

GMGN Skills

GMGNAI

GMGN Agent Skills is an MCP server with 40+ one-click skills for on-chain memecoin trading, token & wallet analytics, smart money / KOL signal monitoring, and token launches on Pump.fun, FourMeme, and Clanker — across Solana, BNB Chain, Ethereum, Base, Monad, and TRON.

Xrpl Utilities

XRPL-Utilities

MCP server for the XRPL-Utilities portfolio. 11 tools across four services:

Lemma — Verifiable Provenance For Ai Agents

lemmaoracle

AI agents make decisions you can't audit. Lemma fixes that with zero-knowledge proofs over confidential documents — selective disclosure, on-chain provenance, no plaintext exposure. Query cryptographically verified attributes from agents in production. Built for regulated industr

Luxxon

daniel-underpass

On-demand live vision for AI agents. Open a session at a lat/lng, receive a JPEG snapshot or WebRTC stream, settle per-second in USDC on Base. The agent-first way to give an LLM eyes on the physical world.

AnchorRegistry

AnchorRegistry

AnchorRegistry is the open provenance layer for the agentic economy. Every digital artifact — code, research, data, models, media, agents, transactions — can be anchored to Base L2 with a permanent, machine-resolvable identifier (an AR-ID). When an AI assistant encounters an SPDX