defluff
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| slop_detectA | Detect AI-slop (clichés, hedges, filler, AI-vocab) in text. Returns slop_score 0-1 + exact slop spans. Deterministic, local, no LLM. Use before returning generated prose to self-check, or to gate/rank drafts. |
| slop_addA | Add a phrase to the slop lexicon so future detections flag it. Use when the user says something is slop / a banned phrase. scope='project' (this repo, shared via git) or 'user' (machine-wide). |
| slop_ignoreA | Mark a phrase as NOT slop (e.g. domain jargon) so it stops being flagged. Use when the user says a flagged phrase is actually fine in this context. scope='project' (this repo) or 'user' (machine-wide). |
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
Each tool targets a distinct operation: detection, addition to lexicon, and ignoring phrases. No overlap in functionality.
All tools follow the consistent 'slop_verb' pattern (slop_add, slop_detect, slop_ignore), making names predictable and clear.
With 3 tools, the server covers the core operations for a slop detection lexicon (add, detect, ignore). It is well-scoped and not excessive.
The set covers detection, addition, and whitelisting, but misses removal of phrases from the lexicon and listing the current lexicon, which are minor gaps.