# loci

> loci — ivenkoolab-loci. Use this tool when you need to unify and query scattered notes and documents, leveraging hybrid retrieval methods for efficient information retrieval. It solves problems of knowledge fragmentation and difficult document searching, providing section-level citations and AI agent accessibility through an MCP server. Ideal for use cases involving large, dispersed datasets and collaborative knowledge management.

Canonical page: https://skillsregistry.net/skills/ivenkoolab-loci  
JSON: https://api.skillsregistry.net/v1/skills/ivenkoolab-loci

## Description

A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-26

## Source

- **Source listing:** [GitHub](https://github.com/IvenKooLab/loci)

## 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": "ivenkoolab-loci"
    }
  }
}
```

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