vs-token-safer
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_symbolA | Find a symbol DECLARATION (class/function/type/var) by name/substring — semantic index, not grep. → capped |
| find_referencesA | Every call site of a symbol (semantic, not grep) — pass |
| goto_definitionA | Jump from a 0-based position to a definition (semantic). |
| diagnosticsA | Compiler/linter errors + warnings (semantic) → capped |
| hoverC | Type/signature of the symbol at a 0-based position (hover) — a few lines, no file open. |
| document_symbolsA | Outline a file — classes/functions/types as a capped |
| read_symbolA | USE INSTEAD OF Read on a file when you only need ONE function/class — returns just that named declaration's source (its span), not the whole file (the read twin of replace_symbol_body). |
| renameA | Rename the symbol at a 0-based position project-wide (semantic — every reference, not a sed). PREVIEW by default (affected |
| replace_symbol_bodyA | Change a whole function/class/method by NAMING it — USE INSTEAD OF Read-the-file + Edit (the outline gives the span, so you skip the whole-file Read and exact-match line-counting). PREVIEW by default; apply=true writes in ONE call. |
| insert_symbolA | Insert text next to a named declaration — position=after (default)|before. The outline gives the point (no Read). PREVIEW by default; apply=true writes. Use instead of Read-then-Edit to add a declaration. |
| safe_deleteA | Delete a named declaration — USE INSTEAD OF Edit-deleting it; REFUSES while still referenced (lists the refs, force=true overrides) so a delete can't silently orphan call sites. PREVIEW by default; apply=true writes. |
| find_filesA | Find files by name (substring or glob like *Manager.cpp) — replaces Bash |
| search_textA | Raw text/regex search (string literals, comments, config — what the symbol index can't answer). Replaces Bash grep when you need text, not symbols. → capped |
| concept_searchA | FUZZY search for a concept you can't name ("how does auth work"). Mines a dictionary from the repo's own identifier+comment co-occurrence (no embeddings, nothing sent) → ranked |
| detect_changesA | Review a diff by IMPACT: git diff → changed symbols → blast radius (callers) + LOW/MED/HIGH risk. → capped |
| vts_adminB | Admin/meta ops (rarely needed): set |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 16 tools
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.
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.
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.
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.