Skip to main content
Glama
JSungMin

vs-token-safer

by JSungMin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

vts_admin

Manage token-safe code search indexes and perform admin operations like discovery, indexing, and read-only git/p4 commands.

Instructions

Admin/meta ops (rarely needed): set op, pass its args in params. discover = searches that bypassed vts; index/preindex/warmup = build indexes; git·p4{argv} = read-only VCS, output compacted.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opYesWhich admin op (see description).
paramsNoArgs for the op, e.g. {"argv":["status"]} for git, {"since":30} for discover.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.1.5
  2. Removedv1.1.2
  3. Changed2 schema fields changedv0.37.3
    • changedInput schema / properties / op / description
      Previous value: -"Which admin operation (see the description)."New value: +"Which admin op (see description)."
    • changedInput schema / properties / params / description
      Previous value: -"Arguments for the op, e.g. {\"argv\":[\"status\"]} for git, {\"since\":30} for discover, {\"projectPath\":\"…\"} for setup."New value: +"Args for the op, e.g. {\"argv\":[\"status\"]} for git, {\"since\":30} for discover."
  4. Changed1 schema field changedv0.33.5
    • changedInput schema / properties / op / enum
      Previous value: -[
-  "setup",
-  "config",
-  "savings",
-  "savings_reset",
-  "discover",
-  "warmup",
-  "gen_compile_db",
-  "git",
-  "p4"
-]New value: +[
+  "setup",
+  "config",
+  "savings",
+  "savings_reset",
+  "discover",
+  "warmup",
+  "preindex",
+  "scope",
+  "index",
+  "gen_compile_db",
+  "git",
+  "p4"
+]
  5. Addedv1.0.3

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full behavioral burden. It only discloses that git/p4 are 'read-only' and that output is 'compacted'. Other ops like 'savings_reset' and 'setup' may have side effects or be destructive, but this is not mentioned. The description is silent on side effects, reversibility, or required permissions for most ops.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with 'Admin/meta ops (rarely needed)', but it is cryptic in places, e.g., 'git·p4{argv}' and the condensed op list. It trades clarity for brevity, making it hard for an agent to parse exactly which ops are covered and what each does.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 12 possible ops, only a few are explained (discover, index/preindex/warmup, git/p4). Ops like setup, config, savings, savings_reset, scope, and gen_compile_db are entirely unaddressed. There is no output schema, so return format is not described. Given the tool's complexity, the description is significantly incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (both parameters documented), so baseline is 3. The description adds value by providing concrete examples: {'argv':['status']} for git and {'since':30} for discover, illustrating the structure of `params`. This goes beyond the generic schema description of 'Args for the op'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it performs 'Admin/meta ops' and lists several sub-operations (discover, index, git, p4) with brief explanations, giving a clear category and some specificity. However, it lacks a single clear purpose since it multiplexes many ops, and the exact scope is fuzzy without examining the enum.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says 'rarely needed' and explains when to use specific ops: 'discover = searches that bypassed vts; index/preindex/warmup = build indexes; git·p4{argv} = read-only VCS'. This provides usage context and implies that normal searches/refactoring should use sibling tools. However, it does not explicitly state when not to use it for ops like setup or config.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools