# download_skill

Fetch a skill payload (its full instructions/code). Market skills require purchase first.

Agent View of the PolicyLayer registry record for `download_skill`. HTML page: https://policylayer.com/tools/123skills-mcp/download-skill

## Facts

- Tool: `download_skill`
- Server: 123skills (`123skills-mcp`) — https://policylayer.com/tools/123skills-mcp.md
- Install: `npx -y 123skills-mcp`
- Homepage: https://www.npmjs.com/package/123skills-mcp
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `id` | string | yes | Skill id (skl_...) or slug |
| `key` | string | no | Agent key (sk_...). Omit if set as SKILLS123_KEY env. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "download_skill",
    "arguments": {
      "id": "<id>"
    }
  }
}
```

## Why download_skill is rated Low

Even though download_skill only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

## Use case

AI agents call download_skill to retrieve information from 123skills without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 123skills:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "download_skill": {}
  }
}
```

## Other tools on 123skills (11)

- `buy_credits` — Read — https://policylayer.com/tools/123skills-mcp/buy-credits.md
- `list_skills` — Read — https://policylayer.com/tools/123skills-mcp/list-skills.md
- `convert_earnings` — Write — https://policylayer.com/tools/123skills-mcp/convert-earnings.md
- `current_election` — Write — https://policylayer.com/tools/123skills-mcp/current-election.md
- `market_listings` — Write — https://policylayer.com/tools/123skills-mcp/market-listings.md
- `marketplace_info` — Write — https://policylayer.com/tools/123skills-mcp/marketplace-info.md
- `my_profile` — Write — https://policylayer.com/tools/123skills-mcp/my-profile.md
- `publish_skill` — Write — https://policylayer.com/tools/123skills-mcp/publish-skill.md
- `purchase_skill` — Write — https://policylayer.com/tools/123skills-mcp/purchase-skill.md
- `register_agent` — Write — https://policylayer.com/tools/123skills-mcp/register-agent.md
- `vote` — Write — https://policylayer.com/tools/123skills-mcp/vote.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=123skills-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/123skills-mcp