Skip to main content
Glama

Related Servers

Alternatives to biz.dfch.SpecMgr

No user-submitted related servers found.

    Related Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP clients to create, list, and read numbered Markdown Architecture Decision Records, and to review designs against pluggable domain rule packs (general, insurance, banking, healthcare, agentic AI) that return PASS/FAIL/UNKNOWN verdicts with evidence. Supports custom rule packs supplied via a local directory of YAML files.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP server for managing an OKF markdown knowledge base, enabling AI agents to query, read, write, and auto-sync architectural decisions and rules via Git.
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      This MCP server enables AI agents to manage artifacts across sessions by providing tools for searching, retrieving, and registering entries in a persistent ledger, ensuring consistency and traceability of agent outputs.
      MIT

    TDQS

    B3.2/5.0

    Scored across 103 tools

    Disambiguation4/5

    Tools follow a clear per-domain verb pattern (create_X/get_X/list_X) plus distinct cross-cutting verbs (update, edit, delete, validate, set_status), so purposes are mostly separable. The main friction is that get_X and parse_X overlap heavily (both read-and-parse a document from disk), and the sheer number of near-identical per-domain variants raises misselection risk.

    Naming Consistency4/5

    The dominant convention is consistent snake_case verb_noun (create_feat, get_feat, list_feat, find_related, validate_plantuml). Minor deviations exist in the ADR option verbs (option_create/option_read/option_update, noun-first) and the diagram readers (get_uc_diagram, get_use_case_package_diagram), but overall the pattern is predictable.

    Tool Count1/5

    103 tools is an extreme mismatch for a spec-management server. The count balloons because each of ~13 document domains gets its own near-identical set of create/get/list/parse/template/example tools, so the surface is a large, repetitive matrix rather than a well-scoped set.

    Completeness4/5

    Coverage is broad and deep: create/read/list/update/edit/delete/set_status/validate exist for nearly all whole-body domains, plus examples, templates, reference graphs, similarity search, and PlantUML tooling. Only minor gaps appear, e.g. delete/validate explicitly exclude ADR and rely on separate ADR-specific tools.

    Maintenance

    ActivityActive
    ResponsivenessWithin a week