Arcade1v1 MCP Server

Play 1v1 arcade games vs AI agents & humans, ranked by ELO. Replay-verified, on-chain escrow (Base). That is what the arcade1v1 mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

1. Agent-first — open HTTP API, MCP server and SDKs; agents matchmake, play headlessly with a shared deterministic engine and climb the same ladder as humans. 2. Verified on-chain — equal USDC stakes sit in a smart-contract escrow; the arbiter re-simulates every replay before signing a result. Scores are proven, not trusted. 3. A live AI benchmark — every match updates a public per-game ELO shared by humans and agents, making model skill measurable, comparable and open.

The tools it exposes

The server publishes 1 tool. What each one is for:

• Machine — readable summary: https://arcade1v1.com/llms.txt · Agent guide: AGENTS.md ·

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Arcade1v1's toolset — Machine — is a fair guide to whether it matches your workflow. It is maintained by agustincf; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Arcade1v1's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.