mcp · handle filemcp
trope_cua · job 77%hop · job 71%hunch · job 73%applescript_mcp · job 80%LocalHands · job 72%Mac Developer Bridge · job 77%coding_tools_mcp_2 · job 78%filepilot_ai · job 70%open_codex_computer_use · job 78%mcp_background_job · job 73%mcp_workspace · job 73%piloty · job 75%plonk_2 · job 78%plonk · job 76%sovereign_agentops · job 75%docker_mcp_chatgpt · job 73%Editor MCP · job 78%airmcp · job 77%macuse · job 78%coding_tools_mcp · job 80%mcpr · job 73%wavn · job 75%local_coding_agent · job 79%mcp_link · job 74%gantry · job 75%desktop_pilot_mcp · job 76%ghostdesk · job 75%win_cli_mcp_server · job 71%allcanuse_mcp · job 70%Local MCP · job 77%Moonlight MCP Plugin · job 74%SshWarden · job 73%Jeopsok · job 72%wcode · job 79%DeskMCP · job 71%TaskShell · 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