# Uma

> Uma — sainellutla-uma. Use this tool when you need to optimize local context for large language models (LLMs) to improve answer accuracy. Uma filters retrieved context to the minimum required, solving problems of information overload and inefficient processing. It takes in raw context and LLM queries as input, outputting optimized context that enhances model performance, ideal for use cases where precision and speed are crucial.

Canonical page: https://skillsregistry.net/skills/sainellutla-uma  
JSON: https://api.skillsregistry.net/v1/skills/sainellutla-uma

## Description

A local RAG context optimizer MCP server that filters retrieved context to the minimum an LLM needs to answer correctly, using a cross-encoder and optional calibration.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/eypgr8kvbn)
- **Repository:** <https://github.com/sainellutla/uma>

## 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": "sainellutla-uma"
    }
  }
}
```

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