# Claude-Gemini Compactor MCP

> Claude-Gemini Compactor MCP — suarezpm-claude-gemini-compactor-mcp. Use this tool when you need to process large files while minimizing token costs and protecting sensitive data. The Claude-Gemini Compactor MCP server routes file processing to local or cloud AI, taking files as input and returning distilled results as output, all while bypassing Claude's context. Ideal for use cases where data privacy and cost efficiency are crucial, such as large-scale data analysis or secure document processing.

Canonical page: https://skillsregistry.net/skills/suarezpm-claude-gemini-compactor-mcp  
JSON: https://api.skillsregistry.net/v1/skills/suarezpm-claude-gemini-compactor-mcp

## Description

An MCP server that bypasses Claude's context by routing file processing to local or cloud AI, saving token costs. It reads files from disk and returns distilled results without Claude seeing the raw content.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/saqyf0huzj)
- **Repository:** <https://github.com/SuarezPM/claude-gemini-compactor-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "suarezpm-claude-gemini-compactor-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/suarezpm-claude-gemini-compactor-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/suarezpm-claude-gemini-compactor-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt