# mcp-winnow

> mcp-winnow — richpeaua-winnow. Use this tool when you need to efficiently interact with multiple MCP servers without overwhelming context. It solves the problem of context bloat by providing meta-tools that progressively disclose and trim results, reducing token usage. The mcp-winnow tool takes in MCP server inputs and outputs trimmed results, making it ideal for use cases where agents require streamlined interactions with multiple servers.

Canonical page: https://skillsregistry.net/skills/richpeaua-winnow  
JSON: https://api.skillsregistry.net/v1/skills/richpeaua-winnow

## Description

Enables agents to use many MCP servers without context bloat by exposing meta-tools (search, load, call, run_code) that reduce token usage via progressive disclosure and result trimming.

## Trust

- **Trust score (0–1):** 0.44
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/j87l6xvpqk)
- **Repository:** <https://github.com/Cambrionic/winnow>

## 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": "richpeaua-winnow"
    }
  }
}
```

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