mcp · handle semdex
cowork_semantic_search · job 79%RepoMind · job 76%mcp_documentation_server · job 75%Homestead · job 71%Local RAG MCP · job 76%OpenCode Document RAG MCP · job 70%markdown-memory · job 72%rag-starter · job 71%code-search · job 74%codebase_rag · job 71%code_memory · job 78%directory_indexer · job 72%kb · job 75%LittleLibrary · job 72%NotedThat · job 71%ontomics · job 73%Zotero KB · job 75%Knowledge Base · job 70%moss · job 78%mcp_local_rag_2 · job 73%Personal Knowledge-Base MCP Server · job 79%Semlith · job 78%nxm-memory · job 74%repo_semantic_search · job 73%Alexandria · job 74%SharePoint Search MCP · job 75%SVDB MCP · job 70%local_faiss_mcp · job 70%MCP RAG Server · job 72%MCP Local Semantics · job 75%sunbeam_memory · job 73%Bismut Vector MCP · job 76%Contour · job 75%RAG Search MCP Server · job 85%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