# mcp-compressor

> Use this tool when you need to optimize token usage in large language models (LLMs) by compressing responses. The mcp-compressor reduces token consumption by intercepting and compressing MCP responses through a pipeline, providing a more efficient interface. It exposes only two meta-tools to the LLM, making it a useful solution for applications where token limits are a concern.

Canonical page: https://skillsregistry.net/skills/zakkii-k-mcp-compressor  
JSON: https://api.skillsregistry.net/v1/skills/zakkii-k-mcp-compressor

## Description

A proxy that intercepts MCP responses to reduce token consumption by compressing them via a pipeline and exposing only two meta-tools to the LLM.

## Trust

- **Trust score (0–1):** 0.33
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/tq437vly6j)
- **Repository:** <https://github.com/zakkii-k/mcp-compressor>

## 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": "zakkii-k-mcp-compressor"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zakkii-k-mcp-compressor` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zakkii-k-mcp-compressor/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