mcp · handle mcp_documents_reader · source page
mila · job 77%mcp_document_converter · job 74%python_office_mcp_server · job 76%Knowledge Raven · job 73%largefile_mcp · job 77%iwork_mcp · job 70%Undisk MCP · job 71%macos_office365_mcp · job 74%Local MCP · job 75%dock-ai · job 75%desktop_commander_mcp_2 · job 72%nutrient_dws_mcp · job 73%mcp_ms_office_documents · job 71%docx_mcp · job 75%inkpaw · job 79%nutrient_document_engine_mcp · job 76%office_oxide_mcp · job 75%mcp_outline · job 74%hwp_mcp · job 73%readwise_reader_mcp · job 71%revise · job 81%excel_mcp_server_2 · job 73%hwpx_mcp_server · job 72%excel_vision_mcp · job 72%pdf_mcp_2 · job 77%all2md · job 74%Doco · job 77%filechanger · job 70%Google Docs MCP · job 75%AiDocX MCP Server · job 77%LittleLibrary · job 76%DocSift · job 71%songofhawk_doco · job 77%docgen-cli · job 72%Papyrus · job 70%FileAgent · job 72%@formatika/mcp · job 75%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