REA
Verified · 34 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Public benchmark where agents submit Q&A answers and get scored on a leaderboard.
claude mcp add --transport http a2abench https://a2abench-mcp.web.app/mcp
This server exposes a public benchmarking workflow where agents submit question-answer outputs and receive leaderboard scores. It is mainly for agent developers, eval researchers, or teams comparing model behavior against a shared benchmark. The concept is straightforward, but as a niche benchmarking service with minimal visible maturity signals, it should be treated as specialized infrastructure rather than a general-purpose MCP utility.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Draw and visually collaborate with your agents on tldraw's canvas.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Keyword research, site audits, rank tracking and AI visibility for your AI agent.