Skip to main content
Glama
wlsdks

ontology-atlas

by wlsdks
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to ontology-atlas

No user-submitted related servers found.

    Related Servers

    • obsidian-local-mcp

      lasheralberto
      F
      license
      B
      quality
      B
      maintenance
      Turns local code repositories into a queryable dependency graph built from AST parsing and git co-edit history, then exposes it alongside an Obsidian vault as persistent memory. Enables context retrieval, impact analysis of proposed changes, and curation of durable prose knowledge through full-text search and Personalized PageRank classification—all fully offline without API keys or embeddings.
      30
      -

    • wikicore

      carlaost
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to build and maintain a shared, git-backed Markdown wiki: they search, file, update and link notes with YAML frontmatter, keep verbatim sources, and optionally read code repos, so knowledge one assistant records is available to all the others. Runs without LLM calls, embeddings or a database, with the vault's own files defining page types, instructions and tools.
      MIT

    • Threadnote

      threadnote
      A
      license
      Not graded
      quality
      A
      maintenance
      Local-first engineering memory and code-graph tools for coding agents. Supports private session handoffs, code-cited knowledge, repository graph inspection, and optional Git-backed team sharing.
      81 npm
      24
      AGPL 3.0

    • tela

      zcag
      A
      license
      A
      quality
      A
      maintenance
      Self-hostable, markdown-native team wiki with a built-in MCP server: agents search, read, and write your wiki pages (ranked Postgres full-text + semantic search, backlink traversal). Plus Atlas, which auto-generates a cited, coverage-checked wiki from your git repos and Jira.
      41
      70
      AGPL 3.0
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 40 tools

    Disambiguation3/5

    Many tools have distinct purposes (validate_wiki vs validate_vault, add_concept vs add_concepts), but the graph-query surface is genuinely overlapping: query_concepts, query_ontology.match_nodes, query_ontology.facets, list_concepts, and find_neighbors all filter/walk nodes, and compile_ontology vs query_ontology have a blurry compile-vs-read boundary. The very long descriptions try hard to carve boundaries, which helps, but an agent could still misselect among the traversal/query tools.

    Naming Consistency4/5

    The vast majority follow a clean verb_noun snake_case pattern (get_concept, add_relations, find_path, validate_vault, patch_concept), with consistent singular/plural batch pairs. A few outliers break the verb-first pattern (git_snapshot, git_status, git_history, connection_info), which are minor deviations rather than chaos.

    Tool Count2/5

    40 tools is well above the 25+ 'too many' threshold for the rubric. The batch variants and code-analysis tools each earn some place, but a monolithic query_ontology with ~35 embedded operations plus overlapping standalone query tools indicates the surface is over-expanded rather than tightly scoped.

    Completeness4/5

    Lifecycle coverage is unusually thorough: concept CRUD plus rename/reclassify/merge/delete, relation add/remove/replace, batch variants, git state, validation, compile, code analysis, project binding, and source reading. Minor gaps remain (e.g., no bulk-delete/bulk-move for concepts), but there are few obvious dead ends.

    Maintenance

    ActivityActive
    ResponsivenessSlow

    Resources