mcp · handle citedock
llmtomd · job 79%PennyOCR MCP · job 75%Synapse Vault · job 79%kb · job 74%Wiki RAG MCP · job 73%MCP RAGdown · job 74%Alexandria · job 75%MCP RAG Server · job 73%Paper Reader MCP · job 74%Mio Memory · job 73%cowork_semantic_search · job 76%zen_mcp_2 · job 76%nectr-mcp · job 75%Papyrus · job 78%myMemory · job 72%mcp_docs_provider · job 73%ytpMD · job 78%Contextator · job 75%rag-starter · job 78%Context Layer · job 77%Markdown Locker · job 77%Farr Cite · job 74%MCP Documentation · job 83%obsidian_graph · job 75%Personal Knowledge-Base MCP Server · job 73%Agentic-RAG-MCP · job 73%LittleLibrary · job 73%notes · job 73%docimprint · job 76%OCR MCP · job 74%DocuGraph MCP · job 78%research-agent · job 73%Mnē-MCP · job 73%Gnosis MCP · job 76%Local Research Library MCP · job 78%Keepygaga RAG · job 78%Privacy First Search Lab · job 74%OpenCode Document RAG MCP · job 75%neuroncite · job 72%DocSift · job 81%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