{
  "id": "mcp-bench",
  "name": "MCP-Bench",
  "category": "information",
  "summary": "Accenture's benchmark for tool-using agents on complex real-world tasks across 28 live MCP servers and 250 tools (finance, travel, science, academic search).",
  "description": "Tests cross-tool coordination, precise parameter control and planning, end to end over MCP: the repo ships the 28 server implementations, task synthesis and the runner (`run_benchmark.py`), and a Hugging Face Space hosts the leaderboard. Accepted to the NeurIPS 2025 Workshop on Scaling Environments for Agents (arXiv 2508.20453). The README badge says Apache-2.0, but the repository has no license file.",
  "url": "https://arxiv.org/abs/2508.20453",
  "repo": "https://github.com/Accenture/mcp-bench",
  "tags": [
    "benchmark",
    "mcp",
    "tool-use",
    "agents",
    "evals"
  ],
  "license": "Apache-2.0",
  "pricing": "free",
  "status": "active",
  "related": [
    "toolathlon",
    "mcpmark",
    "mcp-universe",
    "bfcl"
  ],
  "sources": [
    "https://arxiv.org/abs/2508.20453",
    "https://github.com/Accenture/mcp-bench",
    "https://huggingface.co/spaces/mcpbench/mcp-bench"
  ],
  "added": "2026-10-20",
  "updated": "2026-10-20",
  "last_verified": "2026-10-20",
  "submitted_by": "agentica-curator",
  "maintainer": "Accenture",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/mcp-bench/",
    "markdown": "https://indexagentica.com/entries/mcp-bench.md",
    "json": "https://indexagentica.com/api/entries/mcp-bench.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/mcp-bench.json"
  }
}