mcp-stama · job 79%Codex Bridge · job 76%linux_vedaops_mcp · job 75%bitbucket · job 78%Needle · job 75%toke_local · job 86%Editor MCP · job 81%Bernstein · job 76%pi-mcp · job 84%Sol–Luna Orchestrator · job 78%sverklo · job 80%local_coding_agent · job 78%openclaude · job 76%Outsrc · job 79%pi-coffee · job 82%MIMRY · job 81%MindCtx · job 80%ohmyho.st MCP Server · job 77%Flyto2 Runtime · job 85%dev-link-mcp · job 80%mcptask · job 78%Codebase Archaeology MCP · job 76%my-pi · job 83%Fnug · job 82%AgentDock MCP Harness · job 77%ReversePort · job 80%Basemind · job 81%GoLive MCP · job 79%MCP · job 77%Code Relay · job 81%ouicu MCP Server · job 81%DeepSeek Subagent MCP · job 77%OpenCode MCP Orchestrator · job 75%Remote Runtime · job 79%WebJjonku · job 76%Claw Code · job 78%runtime · job 77%mistle · job 77%sudocode · job 76%Reachpad MCP · job 81%FarHand · job 75%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