llmtrim
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 |
|---|---|
| llmtrim_compressA | Compress an LLM request body and report the token savings. Pass the raw request JSON; get back the compressed request in the same shape plus before/after token counts and the per-stage breakdown. |
| llmtrim_compress_textA | Compress a single text blob and report the token savings. Use this to shrink one chunk (a tool output, a document) rather than a whole request. The text is wrapped in a minimal request, compressed, and the shrunk text is returned. |
| llmtrim_statsA | Report recent savings from the local ledger: tokens trimmed and dollars saved. The same headline figures the |
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 3 tools
The three tools are mostly distinct: llmtrim_compress targets full request bodies, llmtrim_compress_text targets individual text blobs, and llmtrim_stats reports savings. There is slight overlap between the two compress tools, but their scopes are clearly separated by descriptions.
All tool names share the llmtrim_ prefix and mostly use a verb_noun pattern (compress, compress_text, stats). The outlier is llmtrim_stats, which uses a noun rather than an action like get_stats, but the overall pattern remains predictable.
Three tools is well-scoped for a focused utility server: two compression entry points and one stats/reporting tool. Each tool clearly earns its place and the surface is easy to navigate.
For the implied domain of LLM request compression, the set covers compressing whole requests, compressing individual text chunks, and retrieving savings reports. Minor gaps like configuration options or batch compression exist, but the core workflow is complete.