claude_octopus · job 79%mcp_anything · job 77%instapods · job 74%yamltools · job 74%cerbos_mcp · job 73%smart_terminal · job 79%echo_map · job 73%mcp_tasks · job 77%MCPHero Meta-MCP Generator · job 80%heddle · job 79%NEXUSRUN · job 73%mcpd · job 76%skill_mcp · job 76%yepcode_mcp_server · job 75%gridctl · job 73%hs_mcp · job 73%qa_use · job 72%mcpm · job 74%mcp-proxy · job 81%LXAgents Shared Instruction · job 79%Kurd · job 76%oomol_openconnector · job 75%MCP Toolkit Server · job 75%lensa · job 75%ipybox · job 73%toke_local · job 73%mcp_server_node · job 74%wcgw · job 72%skillz · job 72%desktop_commander · job 73%diy_tools_mcp · job 72%yc_plum_hackathon_mcp · job 74%openmcp · job 73%unla_mcp_gateway · job 73%Cabrakan · job 76%MCP Intro · job 73%ToolRush-MCP · job 78%mcp-lens · job 76%qwen-cli-mcp · job 76%mcpserver_local · job 74%mcpwasm · job 73%shell-is-all-you-need · job 75%cyanheads_mcp_server · job 74%mcp_gateway_3 · job 71%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