opensandbox · job 73%Lightrun · job 75%morph · job 74%mistle · job 74%xcode_mcp_wrapper · job 75%TalkCody · job 74%Together Code Interpreter MCP Server · job 72%mcp_memory_gateway_v2 · job 74%ternlang · job 77%computesdk · job 73%litellm_agent_platform · job 73%massgen · job 73%EcoTokens · job 78%cmdshellmcp · job 76%coding_tools_mcp · job 77%wcgw · job 76%freya_mcp_server · job 82%Lambda MicroVM Sandbox MCP · job 81%cpp-analysis-mcp · job 78%pi-mcp · job 82%python_code_validator · job 76%Code Relay · job 77%shrimp_task_manager · job 79%rexec · job 79%LOCUS Engine · job 80%local_coding_agent · job 80%mcp_workspace · job 73%agent_tool · job 80%trueline_mcp · job 74%terminal_mcp · job 75%mk_family · job 81%architect_mcp_server · job 78%coding_tools_mcp_2 · job 74%glass · job 79%dotbot · job 76%Windows Sandbox MCP · job 78%Auto Script MCP · job 76%config2mcp · job 76%Remote Runtime · job 85%Tracea · job 82%Sub-Agents MCP · job 82%Exoproc · job 81%Editor MCP · job 81%runtool · job 76%Agentic SSH · job 77%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