mcp · handle pare_2
azure_devops_mcp_server · job 78%floot_mcp · job 81%aptu-coder · job 83%Fast Agent · job 80%mcp_server_node · job 82%coding-agents-mcp · job 85%agent_tool · job 82%toke_local · job 80%dazbench · job 82%Botoi MCP · job 80%UseAgents · job 80%mcpd · job 79%mcp_gitlab_server · job 82%FleetMCP · job 81%MCP Servers · job 78%ia-qa.com/mcp llm and RAG testing - Dev/QA toolbox · job 83%pare · job 93%Girder · job 81%Agents @Kopern.ai · job 80%x402nano · job 81%aun · job 80%Giljo HQ · job 80%dev.mcp · job 81%toolforte · job 78%TidyCode MCP · job 79%ternlang · job 83%FleetQ · job 80%local-mcp · job 84%runtool · job 80%HomeShed MCP · job 78%Claw Code · job 82%Httpstatus MCP · job 80%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series