Large
sandbox_as_a_service|Large|unknown|hour
mcp · handle sandbox_as_a_service · source page
sandbox_as_a_service|Large|unknown|hour
sandbox_as_a_service|Medium|unknown|hour
sandbox_as_a_service|Small|unknown|hour
FileMCP · job 73%chat2shell · job 71%cua · job 76%opensandbox · job 79%ghostdesk · job 84%docker_mcp_chatgpt · job 75%mcpd · job 70%Together Code Interpreter MCP Server · job 71%mcp_background_job · job 75%terminal_mcp · job 74%mcp_test_2 · job 73%computesdk · job 77%WinAgent Sandbox MCP · job 70%Computer-Using Agents (CUAs) Infrastructure · job 78%architect_mcp_server · job 76%WebJjonku · job 75%MCP File Server · job 70%nanosandbox · job 74%Project Moon · job 73%Fishbowl · job 78%Lambda MicroVM Sandbox MCP · job 83%Kali MCP Sandbox · job 73%Poltr · job 73%dev-link-mcp · job 72%execkit · job 72%burrowbox · job 79%briq · job 72%ForgeBridge · job 72%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