Skip to main content
Glama
MatheusPCardoso

caveman-core-mcp

by MatheusPCardoso
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

caveman-core-mcp

MCP server that teaches LLMs to respond in compressed caveman-style prose.
Cuts output tokens ~65% while keeping full technical accuracy. Zero external dependencies.

What it exposes

Prompts

Name

Effect

caveman

Full mode — drops articles, fillers, fragments OK

caveman_lite

Lite mode — removes filler/hedging, keeps articles and full sentences

caveman_ultra

Ultra mode — maximum compression, one word when one word enough

Resources

URI

Content

caveman://rules

Full ruleset text

caveman://rules/lite

Lite ruleset text

caveman://rules/ultra

Ultra ruleset text

Tools

Name

Description

compress_text

Post-process any text through the compression algorithm

Related MCP server: caveman-mcp

Install

{
  "mcpServers": {
    "caveman": {
      "command": "node",
      "args": ["/path/to/caveman-core-mcp/src/index.js"]
    }
  }
}

Or with npx after publishing:

{
  "mcpServers": {
    "caveman": {
      "command": "npx",
      "args": ["caveman-core-mcp"]
    }
  }
}

Usage

Inject via prompt (recommended)

Use the caveman prompt at session start. The host sends the ruleset as context and the LLM adopts compressed mode for the rest of the session.

Inject via resource

Read caveman://rules and include the text in your system prompt manually.

Post-process text

Call the compress_text tool to strip filler from any already-generated text.

{
  "name": "compress_text",
  "arguments": {
    "text": "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by a missing semicolon."
  }
}

Returns:

{
  "content": [{ "type": "text", "text": "Issue caused by missing semicolon." }],
  "_meta": { "before": 95, "after": 35, "savedPercent": 63 }
}

Requirements

  • Node.js >= 18

  • No npm dependencies

Origin

Based on caveman by Julius Brussee (MIT).

  • src/compress.js — derived from src/mcp-servers/caveman-shrink/compress.js

  • src/skill.js — derived from skills/caveman/SKILL.md

  • src/index.js — new standalone MCP server built on top of the above

Available Tools

1 tool
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.

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesText to compress.

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden of disclosure. It details exactly what transformations occur (removing articles, fillers, pleasantries, hedges) and what is preserved (code blocks, URLs, paths, identifiers), plus the output (compressed text and character counts). It does not mention potential unintended rephrasing or irreversible effects, but overall it is transparent beyond a generic 'compress' statement.

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

Conciseness5/5

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

Three compact sentences: the first states the core function, the second lists what is removed, the third lists what is preserved and the return value. Every sentence contributes essential information; no filler or redundancy.

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

Completeness5/5

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

For a tool with one simple parameter, full schema coverage, no output schema, and no sibling tools, the description fully covers the tool's behavior: the transformation rules, the preserved elements, and the return format (compressed text and character counts). Nothing essential is missing.

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

Parameters3/5

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

The schema has 100% coverage with a single parameter 'text' described as 'Text to compress.' The description adds that the input is prose text, which slightly extends the schema's generic description, satisfying the baseline expectation. No additional parameter details are needed given the simple structure.

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 compresses prose text using 'caveman rules,' enumerates what is removed (articles, fillers, pleasantries, hedges) and preserved (code blocks, URLs, paths, identifiers), and specifies the return value. This is a specific verb+resource with detailed scope that leaves no doubt about the tool's function.

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 implies appropriate use for compressing prose text, especially when preserving technical elements like code blocks and URLs. No explicit alternatives are given since there are no sibling tools, but the context ('Compress prose text') provides clear usage direction without exclusions.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedcompress_text
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap. The tool's purpose is clearly defined.

Naming Consistency5/5

The tool name 'compress_text' follows a clear verb_noun pattern, which is consistent and descriptive despite being the only tool.

Tool Count3/5

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.

Completeness5/5

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.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers