mcp · handle mcp_python_interpreter
lmstudio_toolpack · job 78%prims_mcp_server · job 85%ipybox · job 79%matlabmcp · job 82%kai · job 72%codeinterpreter · job 72%open_computer_use_2 · job 75%GenPark In-Process Python REPL Skill · job 76%Model Context Protocol Servers · job 81%Project MCP · job 73%System Control MCP Server · job 74%Nexus MCP Enterprise Gateway · job 73%code_sandbox_mcp · job 73%nmcli MCP Server · job 73%mypr-mcp · job 77%multitool · job 80%Code Interpreter Agent by Nova · job 77%CodeMode · job 78%LocalForge · job 81%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