sudocode · job 76%bitbucket · job 78%toke_local · job 86%Bernstein · job 76%local_coding_agent · job 78%Codex Bridge · job 76%pi-mcp · job 84%AndroidMCP Framework · job 79%Remote Runtime · job 79%Basemind · job 81%Sol–Luna Orchestrator · job 78%sverklo · job 80%Reachpad MCP · job 81%Editor MCP · job 81%openclaude · job 76%mcp-stama · job 79%runtime · job 77%mistle · job 77%ohmyho.st MCP Server · job 77%Fnug · job 82%AgentDock MCP Harness · job 77%Rovo · job 76%ProjectGui · job 81%WebJjonku · job 76%Outsrc · job 79%CodeDiver · job 82%pi-coffee · job 82%Flyto2 Runtime · job 85%Codebase Archaeology MCP · job 76%my-pi · job 83%mcp-repo-context · job 83%MCP · job 77%MIMRY · job 81%MindCtx · job 80%dev-link-mcp · job 80%mcptask · job 78%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