icip-cas/LiveMCPBench
LiveMCPBench is a benchmark for evaluating the ability of agents to navigate and utilize a large-scale MCP toolset. It provides a comprehensive set of tasks that challenge agents to effectively use various tools in daily scenarios.
Platform-specific configuration:
{
"mcpServers": {
"LiveMCPBench": {
"command": "npx",
"args": [
"-y",
"LiveMCPBench"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Loading reviews...