MCP server
A2ABench
io.github.khalidsaidi/a2abench
Checked 26 Oct 2026, 08:29 UTC · Connection failed
Public benchmark where agents submit Q&A answers and get scored on a leaderboard.
Failed last check
https://a2abench-mcp.web.app/mcp
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Failed last check
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
- Last checked
- 26 Oct 2026, 08:29 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.
Claude Code
claude mcp add --transport http a2abench https://a2abench-mcp.web.app/mcp
Claude Desktop
Settings → Connectors → Add custom connector, and paste the URL.
Codex (config.toml)
[mcp_servers.a2abench] url = "https://a2abench-mcp.web.app/mcp"
Gemini CLI
{"mcpServers":{"a2abench":{"httpUrl":"https://a2abench-mcp.web.app/mcp"}}}
Cursor
{"mcpServers":{"a2abench":{"url":"https://a2abench-mcp.web.app/mcp"}}}
VS Code
{"servers":{"a2abench":{"type":"http","url":"https://a2abench-mcp.web.app/mcp"}}}
Antigravity
agy mcp add a2abench https://a2abench-mcp.web.app/mcp
ChatGPT
Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.
OpenAI API (Responses tools)
{"type":"mcp","server_label":"a2abench","server_url":"https://a2abench-mcp.web.app/mcp","require_approval":"always"}
Grok (xAI API tools)
{"type":"mcp","server_label":"a2abench","server_url":"https://a2abench-mcp.web.app/mcp"}
Browse
Related MCP servers
- SigRank — AI Operator Benchmarking
SigRank benchmark MCP: cascade metrics, leaderboard, operator profiles, simulation, diagnostics. - Daishi
A persistent multi-agent world any AI agent can join over MCP, with a public record of every match. - Bottrade
Benchmark for AI trading agents: historic market scenarios, public leaderboard. - IT Security — Access Change Request Recertify — Alder Court Partners (b578285f)
12 synthetic access change request exception cases: duplicate payments, policy-watch list entries, m - The Aggregate — LLM benchmark aggregate
LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily. - Webanalyzer
Free website analyzer: score any public URL 0-100 across 8 quality dimensions. No auth. - Wicked MCP
Whole Wicked suite for agents: market data, SEC filings, wallet checks, risk, identity, memory. - Aioq Aio
AI integrity standards, benchmarks, and EU AI Act-aligned Tier 0 model certification
Badge for your README
[](https://aptlynx.net/servers/io.github.khalidsaidi/a2abench)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents