Skip to main content
Glama
JSungMin

vs-token-safer

by JSungMin

Related Servers

Alternatives to vs-token-safer

No user-submitted related servers found.

    Related Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Code-search engine that parses TypeScript and JavaScript with a real AST, stores the symbol graph in SQLite, and serves AI assistants exact matching declarations (functions, classes, types) via BM25 fused with declaration-exact ranking — saving tokens by returning only the relevant code instead of whole files.
      50 npm
      3
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Local-first code retrieval for AI agents — cuts codebase context from thousands of tokens to a few hundred, with zero hallucinated file paths.
      3
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables LLM agents to efficiently understand and navigate a codebase by providing semantic search over symbols and a reference graph, replacing expensive grep/glob calls with structured tools like definition lookup, caller/callee queries, and change-impact analysis.
      3
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Fast semantic code search for AI agents — find symbols, references, and callers across any codebase.
      9
      Apache 2.0
    • A
      license
      Not graded
      quality
      A
      maintenance
      Local-first code intelligence MCP server that enables coding agents to search code, inspect structure, read exact ranges, and explore Git history with explicit token budgets.
      24
      Apache 2.0

    TDQS

    A3.7/5.0

    Scored across 16 tools

    Disambiguation5/5

    Each tool targets a distinct operation: search, reference, definition, diagnostics, hover, outline, and symbol edits are clearly separated. Even the three search tools (search_symbol, search_text, concept_search) are explicitly differentiated by whether the input is a symbol name, raw text, or a fuzzy concept.

    Naming Consistency3/5

    Most tools follow a readable verb_noun snake_case pattern (find_references, replace_symbol_body, insert_symbol), but there are notable deviations: concept_search reverses the search_* convention, vts_admin is a cryptic meta-tool name, and diagnostics/hover/rename are bare nouns or verbs. The set is still readable, but the naming pattern is not consistently applied.

    Tool Count4/5

    At 16 tools, the server is slightly above the usual sweet spot, but each tool maps to a distinct code-intelligence or symbol-editing capability. There is minimal redundancy, and the breadth is justified by the wide range of navigation, search, editing, and safety operations covered.

    Completeness5/5

    The set provides full symbol lifecycle coverage: read_symbol for reading, insert_symbol for creating, replace_symbol_body and rename for updating, and safe_delete for deleting. It also covers navigation, search, diagnostics, diff impact analysis, and file discovery, so agents have no obvious dead ends when working with code symbols.

    Maintenance

    ActivityActive
    ResponsivenessUnresponsive