caveman-core-mcp
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 | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| compress_textA | Compress prose text using caveman rules. Removes articles, fillers, pleasantries, hedges. Preserves code blocks, URLs, paths, identifiers. Returns compressed text and character counts. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| caveman | Activate caveman mode (full). LLM responds in compressed prose — drops articles, fillers, pleasantries while keeping full technical accuracy. Cuts output tokens ~65%. |
| caveman_lite | Activate caveman lite mode. Removes filler and hedging but keeps articles and full sentences. Professional and tight without fragments. |
| caveman_ultra | Activate caveman ultra mode. Maximum compression — strips conjunctions when meaning stays clear, one word when one word enough. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Caveman Rules | Full caveman compression ruleset. Inject into system prompt to activate token-efficient mode. |
| Caveman Rules (lite) | Lite caveman ruleset — removes filler/hedging, keeps articles and full sentences. |
| Caveman Rules (ultra) | Ultra caveman ruleset — maximum compression, one word when one word enough. |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap. The tool's purpose is clearly defined.
The tool name 'compress_text' follows a clear verb_noun pattern, which is consistent and descriptive despite being the only tool.
The server has just one tool, which is on the borderline of feeling thin. However, the tool's narrow scope (caveman-style text compression) makes the count acceptable.
The tool fully delivers on its stated purpose of compressing text, including preserving code blocks and returning character counts. No obvious gaps exist for this specific domain.