mcp · handle synapse_vault
librarian_mcp · job 74%flint_note_mcp · job 73%memento_2 · job 75%obsidian_graph · job 83%turbovault · job 74%sourcebook · job 76%Keepygaga RAG · job 89%Local Research Library MCP · job 78%Papyrus · job 78%syncpen · job 75%DocSift · job 80%mcp_obsidian_4 · job 72%Ferumind · job 76%sunbeam_memory · job 72%zen_mcp_2 · job 82%Awareness Local · job 78%omniclip_rag · job 84%project_synapse_mcp · job 72%obsidian_llm_wiki · job 80%seeklink · job 77%Knowledge Base · job 74%OKF Agent Memory · job 76%agentgraph_server · job 74%knownbase · job 80%kept · job 73%agent_library · job 76%markdown_downloader · job 76%Waikiki · job 73%okc-mcp · job 83%LittleLibrary · job 80%ragmark · job 81%Agent Knowledge Memory Wiki · job 81%agentbrain · job 81%solomd · job 85%LiteContext CLI · job 78%mcp-docs-ask · job 75%braintube_mcp · job 79%Markdown Locker · job 80%llmtomd · job 79%directory_indexer · job 75%okfshare CLI and MCP Server · job 82%OpenCode Document RAG MCP · job 75%mcp_docs_provider · job 83%CodeAtlas · 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