coding_tools_mcp_2 · job 87%ternlang · job 77%largefile_mcp · job 79%mithril · job 81%coding_tools_mcp · job 86%basic_fns_mcp · job 81%Agentic SSH · job 80%Universal FS MCP · job 84%Mafsil · job 82%KMJ CodeBridge · job 78%Corulix · job 83%SshWarden · job 82%Windows Sandbox MCP · job 79%wspace · job 83%cmdshellmcp · job 79%Raccoon MCP · job 81%Project Moon · job 79%local_coding_agent · job 85%wcgw · job 84%Bash MCP · job 81%AgentDock MCP Harness · job 80%FileMCP · job 78%The Boring Crocodile · job 80%CodeMCP · job 77%Lambda MicroVM Sandbox MCP · job 81%Flyto2 Runtime · job 84%TaskShell · job 77%mcp-stama · job 81%Rob Desktop Commander · job 81%pi-mcp · job 81%Rig Bridge · job 80%LOCUS Engine · job 79%WebJjonku · job 86%Agent Env MCP · job 81%Free Coding Agent · job 80%rexec · job 82%Anvil Bridge · job 79%Remote Runtime · job 84%taskdeck · job 80%tussh · job 79%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