loci-mcp
Related Servers
Alternatives to loci-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityAmaintenanceEnables Claude and other MCP-compatible clients to create, link, search, explore, and synthesize atomic Markdown notes organized as a connected knowledge graph with tags and semantic relationships.-
- FlicenseNot gradedqualityAmaintenanceEnables Claude and other MCP-compatible clients to create, link, search, explore, and synthesize atomic notes in a bidirectional knowledge graph. Supports tags, note types, semantic link types, and dual Markdown/SQLite storage for AI-assisted knowledge management.-
- FlicenseNot gradedqualityAmaintenanceEnables Claude and other MCP-compatible clients to create, link, explore, and synthesize atomic notes with semantic relationships, tags, search, and a Markdown-backed knowledge graph.-
- FlicenseNot gradedqualityAmaintenanceEnables creating, linking, tagging, searching and exploring atomic notes that form a networked knowledge graph, with bidirectional semantic link types and markdown files as the source of truth. Supports knowledge creation, exploration and synthesis through Claude and other MCP-compatible clients.-
- FlicenseNot gradedqualityAmaintenanceEnables creating, linking, searching, and synthesizing atomic notes stored as human-readable Markdown files with a rebuildable SQLite index, forming a navigable knowledge graph through typed semantic relationships, tags, and distinct note types. It lets Claude and other MCP-compatible clients capture fleeting ideas, explore linked notes across domains, and surface central, similar, or orphaned notes for further synthesis.-
- FlicenseNot gradedqualityAmaintenanceEnables Claude and other MCP-compatible clients to create, link, tag, search, and update atomic notes stored as Markdown files, building a bidirectional knowledge graph with semantic relationships. Also supports exploring and synthesizing that graph through tools that surface linked, similar, central, and orphaned notes.-
TDQS
Scored across 39 tools
Most tools target a distinct resource+action (write/read/patch/delete/search on vault nodes, separate versioning, inbox, ontology, and asset tools). A few boundaries blur: search_vault vs find_nodes vs resolve_mentions all retrieve nodes, and define_type competes with write_meta(file="ontology-user") which is also described as the way to register a user type. Descriptions do help sort these out, but the registration overlap is a real source of misselection.
Nearly everything is snake_case verb_noun (write_vault, read_meta, scan_inbox, define_relation, execute_inbox_file_batch). The only wrinkle is inconsistent retrieval verbs — query_*, find_*, search_vault, get_inbox_plan, list_vault, read_vault — so similar read operations don't share a prefix. Still very readable and predictable overall.
39 tools is heavy for a single server and sits in the top band of the rubric. The domain is genuinely broad (vault CRUD, git-style history, ontology extension, assets, staged inbox, skills), so most tools earn their place, but several could be folded together (find_nodes/search_vault, define_type/write_meta).
Coverage is unusually thorough: full node lifecycle plus versioning/restore, filtered and keyword retrieval, graph queries, ontology/relation extension, asset registration, and a staged-inbox workflow. Minor gaps remain — search_vault only matches title and summary (no body full-text search), and there is no rename/move or delete operation for user-defined types/relations beyond overwriting ontology-user.