Headroom Mini
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 |
|---|---|
| compress_codeB | Semantic code compression (removes comments + whitespace) |
| compress_jsonB | Minify JSON safely without breaking structure |
| optimize_promptB | Moves dynamic fields (timestamps / UUIDs) to end for better cache performance |
| redact_contentB | Redacts oversized code / logs and replaces them with a reversible placeholder |
| hydrateC | Restores content from HEADROOM_REDACTED placeholders |
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 5 tools
Each tool targets a distinct operation: compression of code vs JSON, redaction, hydration, and prompt optimization. There is no functional overlap.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., compress_code, redact_content), making them predictable for an agent.
With 5 tools, the server is well-scoped for content manipulation tasks. Each tool serves a clear purpose without unnecessary redundancy.
The set covers compression, redaction, hydration, and prompt optimization, but lacks a decompress tool for JSON minification and potentially other common formats, leaving a minor gap.