# mcp-sieve

> mcp-sieve — dimarch0x-mcp-sieve. Use this tool when you need to simplify access to multiple MCP servers by consolidating tool options, reducing complexity for Large Language Models (LLMs) to improve efficiency and accuracy. It solves the problem of overwhelming LLMs with numerous tool choices, streamlining the process by presenting only two tools. This proxy takes in MCP server requests and outputs a filtered selection of tools, ideal for use cases involving git and complex server management.

Canonical page: https://skillsregistry.net/skills/dimarch0x-mcp-sieve  
JSON: https://api.skillsregistry.net/v1/skills/dimarch0x-mcp-sieve

## Description

Semantic tool selection proxy for MCP servers — LLM sees 2 tools instead of dozens

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/dimarch0x/mcp-sieve)

## 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": "dimarch0x-mcp-sieve"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dimarch0x-mcp-sieve` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dimarch0x-mcp-sieve/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