mcp · handle capyhub
local-mcp · job 77%MCP Google Service · job 80%google_mcp · job 82%withone_one · job 82%dev.mcp · job 83%MCP on Azure · job 78%mcp_microsoft_office · job 78%gitlab_mcp · job 84%Rogue Atlassian MCP · job 78%COAGENTS · job 81%pare · job 79%mcp_assistant · job 79%smart_terminal · job 81%mcp_gitlab_server · job 84%Enterprise MCP Gateway · job 79%Zambo · job 82%mcp_toolkit_2026 · job 79%Model Context Protocol Servers · job 79%opentabs · job 78%Conector · job 82%Gate22 · job 82%skuuymcp · job 80%Team-governed Fentaris Proxy · job 79%MCP for Copilot · job 79%EcoScan · job 78%forgemax · job 79%google_workspace_mcp · job 81%working_machines · job 81%MCPGate · job 80%stackone · job 81%floot_mcp · job 82%b_board · job 80%UnClick · job 81%bluenexus_mcp · job 80%jfxsoft.mcp · job 82%OpenConnector · job 82%min-mcp · 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