clangaroo · job 76%Kilo · job 75%context_engineering · job 80%Kilo Code · job 76%Cline · job 76%codex_mcp_tool · job 79%morph · job 74%GitHub Copilot · job 72%xcode_mcp_wrapper · job 75%mcp_server_vscode · job 74%rtfm · job 77%project_mapper · job 77%codescout · job 77%symgraph · job 71%javalens_mcp · job 74%sift · job 75%graphmemory_ide · job 71%local_coding_agent · job 75%mcp_ragex · job 72%browser_mcp · job 76%claude_code_mcp · job 74%atlas_scout_mcp · job 71%edt_mcp · job 76%mcp-stama · job 80%wcgw · job 76%indxr · job 74%debugmcp · job 75%pi-mcp · job 74%bifrost_mcp · job 72%desktop_commander_mcp · job 76%axon_mcp_server · job 76%drift · job 75%Code Tutor Narrator · job 76%vscode_mcp · job 81%uizze · job 77%docent.nvim · job 72%sverklo · job 74%synapse · job 71%sourcerer_mcp · job 71%codegraff · job 76%leankg · job 74%code_screenshot_mcp · job 72%Agent Env MCP · job 73%fossil_mcp · job 71%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