# toolpipe

> toolpipe — kunalkaul-toolpipe. Use this tool when you need to efficiently manage large tool outputs and keep them out of context, passing MCP results by reference instead of through the LLM. It solves problems of data overload and context clutter, providing a data-plane proxy for streamlined output handling. Ideal for use cases involving large data outputs, such as git operations, to optimize performance and reduce context size.

Canonical page: https://skillsregistry.net/skills/kunalkaul-toolpipe  
JSON: https://api.skillsregistry.net/v1/skills/kunalkaul-toolpipe

## Description

Pass MCP results by reference, not through the LLM — a data-plane proxy that keeps large tool outputs out of context.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/kunalkaul/toolpipe)

## 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": "kunalkaul-toolpipe"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kunalkaul-toolpipe` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kunalkaul-toolpipe/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