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