mcp_toolkit_2026 · job 80%aptu-coder · job 82%gitlab_mcp · job 80%OpsMCP · job 81%dev.mcp · job 78%rust_mcp_filesystem · job 78%Sideyard · job 80%pare · job 79%local_coding_agent · job 80%basic_fns_mcp · job 78%Aura · job 79%mxlore · job 80%agent_tool · job 83%Ganado Bridge · job 80%mcpd · job 78%Model Context Protocol · job 78%Memorix · job 79%coding-agents-mcp · job 85%fusional · job 80%mcp_gitlab_server · job 77%system-command-mcp · job 80%floot_mcp · job 81%toke_local · job 79%Local Terminal MCP · job 82%KMJ CodeBridge · job 82%Universal AI Bridge · job 80%HomeShed MCP · job 79%Engineering Context MCP · job 78%capyhub · job 77%JecBridge · job 86%Gesso · job 82%MemCastle · job 84%PC Bridge · job 79%Rob Desktop Commander · job 81%Strata Coder · job 80%DeskTether · job 79%skuuymcp · job 78%MCP for Copilot · job 80%FleetMCP · job 77%code-executor-mcp · job 83%FINNESS MCP Server · job 79%Open Remote MCP · job 78%Scrumboy · job 77%RelayForge MCP · job 84%runtool · job 77%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