mcp · handle stateful_agent_mcp
Bernstein · job 73%pi-coffee · job 80%bitbucket · job 77%MCP GitHub Repository Orchestrator · job 74%rustkb · job 77%LogNexus · job 78%ProjectGui · job 77%sudocode · job 75%Forja MCP · job 77%buggazi · job 79%mcp-repo-context · job 76%ReversePort · job 77%pi-mcp · job 78%watercooler · job 78%mcptask · job 77%Rovo · job 75%Fnug · job 76%Norma MCP Server · job 73%Agent Env MCP · job 82%Stateful Coding Agent MCP · job 77%mistle · job 73%Flyto2 Runtime · job 75%Crabrix SDK and MCP · job 75%mdkg · job 78%murphy-mcp · job 76%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