mcp · handle modelcontextprotocol
lmstudio_agent_mcp · job 76%agents_mcp_gateway · job 77%mediaengine · job 76%agent_library · job 75%ipybox · job 79%omniclip_rag · job 76%toke_local · job 76%browser_rendering · job 77%tuls · job 84%Aura · job 78%Jeopsok · job 77%songofhawk_doco · job 78%basic_fns_mcp · job 82%rust_mcp_filesystem · job 78%pare · job 77%mcp_toolkit_2026 · job 77%mission · job 79%ChanFS MCP · job 76%smart_terminal · job 82%utilsforagents-mcp · job 76%joshua_wkl4_bristlecone_logic · 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