# ard-publish

> ard-publish — neuronto-ard-publish. Use this tool when you need to make your API, server, or AI agent discoverable by other AI agents. It builds, validates, and verifies an Agentic Resource Discovery (ARD) manifest, solving discovery and integration problems for AI systems. The ard-publish tool takes in API or server details as input and outputs a validated ARD manifest, streamlining the discovery process for AI agents.

Canonical page: https://skillsregistry.net/skills/neuronto-ard-publish  
JSON: https://api.skillsregistry.net/v1/skills/neuronto-ard-publish

## Description

Make your API, MCP server or AI agent discoverable by AI agents. Build, validate and verify an Agentic Resource Discovery (ARD) manifest.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/neuronto/ard-publish)

## 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": "neuronto-ard-publish"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/neuronto-ard-publish` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/neuronto-ard-publish/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