mcp · handle mcpgrade
MCP Studio · job 76%mcppedia · job 80%onmcp · job 82%MCP Context Budget · job 82%AgentShield MCP Inspector Lite · job 82%MCP Triage · job 76%Sample MCP Server · job 80%mcp_retrieval_probe · job 78%Assay · job 79%Toolrank · job 84%policylayer_registry · job 76%MCP Verdict · job 78%aio_geo · job 78%Brawler MCP Server · job 74%MCP Latchpoint · job 73%ProofRail · job 75%mcpulse · job 76%mcpindex · job 83%mcp-lens · job 76%joshua_wkl4_bristlecone_logic · job 78%dicenzo MCP Servers · job 78%mcp_judge · job 75%toolweather · job 76%The MCP Census · job 81%mcp_server_cli_dify · job 73%mcp_anything · job 75%DeepSleuth · job 78%askpod · job 76%MCP Server Inspector · job 82%Rogue MCP Detection · job 78%mcp-ml-tools · 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