MCP · A2A · x402 · agentndx.ai llms.txt MCP endpoint
BrowseAI & Models → MCP Bench
MCP Bench
Benchmarking framework by Accenture for evaluating LLM tool-use via MCP. End-to-end pipeline assessing how effectively models discover, select, and use tools.
MCP unverified
Transport stdio
Auth none
Endpoint python -m mcp_bench
01 Benchmark LLM tool-use capabilities across models
02 Evaluate tool discovery and selection accuracy
03 Compare model performance on complex real-world MCP tasks
benchmarking evaluation tool-use llm research
Machine-readable: /api/servers.json  ·  JSON-LD schema embedded in <head>