Skip to main content
Glama
JSungMin

vs-token-safer

vts_admin

Configure settings, monitor token savings, discover bypassed searches, prebuild indexes, and run read-only VCS commands for the vs-token-safer server.

Instructions

vs-token-safer admin/meta operations (rarely needed reflexively) — set op and put that op's args in params: • setup {projectPath,backend,maxResults,genCompileDb,clangdCmd} — configure (writes config; /reload-plugins after) • config {} — show effective settings · savings {graph,daily,history} — tokens saved (local) · savings_reset {} — clear it • discover {since,all,learn,projectPath} — find code searches that BYPASSED vts (missed savings) • warmup {projectPath,backend} — pre-build the index so later searches are fast • preindex {projectPath,backend} — build the index ahead of time (clangd: a static --index-file via clangd-indexer if present, honoring scope) • scope {projectPath} — show the indexing scope + TU stats + top-level dirs to pick from (set via setup --scope) • index {projectPath,status} — build the committable .vts-index/symbols.jsonl (tree-sitter; instant cold-start tier, no toolchain); status shows the current one • gen_compile_db {projectPath,apply,inTree,engineRoot,target,…} — generate the UE clangd compile DB • git {argv|args,projectPath} · p4 {argv|args,projectPath} — run a READ-ONLY VCS command, output compacted (mutating REFUSED)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opYesWhich admin operation (see the description).
paramsNoArguments for the op, e.g. {"argv":["status"]} for git, {"since":30} for discover, {"projectPath":"…"} for setup.
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses read-only vs. mutating behavior (e.g., git/p4 are READ-ONLY, mutating REFUSED) and side effects (e.g., setup writes config requiring /reload-plugins). However, it omits details like authentication or rate limits.

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

Conciseness4/5

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

The description is dense but well-structured with a general introduction followed by bullet-point sub-operations. It is front-loaded with the purpose and efficiently organizes multiple ops. Minor verbosity in some param descriptions could be tightened.

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

Completeness4/5

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

Given no output schema, the description adequately explains return values for most ops (e.g., 'savings shows tokens saved', 'scope shows indexing scope'). However, some operations like 'setup' lack explicit return info. Overall, it covers the necessary context for an admin tool.

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

Parameters5/5

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

The description adds extensive meaning beyond the input schema, detailing each op's specific parameters and behavior. For example, it explains 'discover' takes {since,all,learn,projectPath} and finds missed savings. The schema only provides enum values and a generic params object, so the description is essential.

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

Purpose5/5

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

The description clearly states the tool is for 'vs-token-safer admin/meta operations' and lists specific operations. It distinguishes from sibling tools (e.g., diagnostics, find_files) which are code-focused, while vts_admin is for admin tasks.

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?

The description notes it is 'rarely needed reflexively', implying it should not be used automatically. It provides explicit usage for each operation, but lacks direct comparison to alternatives or when-not-to-use cases.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JSungMin/vs-token-safer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server