mcp · handle shrimp_task_manager
drift · job 75%in_memoria · job 80%guild · job 75%codemem · job 82%deeplucid3d_mcp · job 76%mcp_memory_gateway_v2 · job 73%codingbuddy · job 76%getpapi · job 83%barbell-tools · job 73%Lightrun · job 82%doriku · job 78%operations · job 74%sync · job 78%egc · job 73%mk_family · job 82%roo_logger · job 74%Relay · job 83%mithril · job 79%taskflow_mcp · job 79%world_model_mcp · job 78%dotbot · job 83%vibe_coder_mcp · job 78%heimdall_mcp_server · job 79%Docket · job 80%kawacode_mcp · job 82%Kiokuko · job 74%dmx · job 76%kaban · job 77%board_mcp · job 74%AgentSeed · job 77%retasc · job 76%objective · job 77%metatron · job 78%enhanced_mcp_memory · job 74%infrawise · job 81%conxt · job 80%codetree · job 72%mcp_debugger_2 · job 72%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