# uldl

> Use this tool when you need to persistently store and manage files for AI agents, solving problems of data loss and version control. It provides upload, download, and versioning capabilities via MCP and curl interfaces, accepting file inputs and returning stored files as outputs. Ideal for use cases requiring reliable file storage and retrieval in AI-driven applications.

Canonical page: https://skillsregistry.net/skills/sh-uldl-uldl  
JSON: https://api.skillsregistry.net/v1/skills/sh-uldl-uldl

## Description

Persistent file storage for AI agents via MCP and curl. Upload, download, and version files.

## Trust

- **Trust score (0–1):** 0.80
- **Verification tier:** unverified

## Facts

- **Version:** 0.1.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-09

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/sh.uldl%2Fuldl)

## Use it

MCP endpoint published by the skill: `https://uldl.sh/api/mcp`

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": "sh-uldl-uldl"
    }
  }
}
```

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