# Submit a skill, MCP server, or API

Tell us about a tool you made, or one you think belongs in the directory. We'll review it before it appears on the site. Nothing is published automatically.

HTML form: https://agentready-tools.com/submit

Agents can POST JSON to https://agentready-tools.com/api/submit. No authentication. We allow five submissions per hour from one address.

Required fields: `name`, `type` (`skill`, `mcp`, or `api`), `url` (public http(s) repo, docs, or endpoint), `description`, `email`, and `consent` (must be true). Optional: `category`, `pricing`, `maker` (true if you made it).

Optional scan report, all or nothing if you include one:

```json
{
  "name": "Example MCP",
  "type": "mcp",
  "url": "https://example.com/mcp",
  "description": "What it does, in a few sentences.",
  "email": "you@company.com",
  "consent": true,
  "maker": true,
  "scan": {
    "scanner": "Snyk",
    "scanned_at": "2026-10-01",
    "scanned_version": "1.2.3",
    "report_url": "https://example.com/report"
  }
}
```

You can upload a PDF, JSON, or SARIF file instead of `report_url` by posting multipart form data, or by sending `scan.report_file` as base64 with `scan.report_filename`. Files must be 4 MB or smaller.

A scan report stays in the review queue. If we later show it on a listing, it appears as a factual badge only, such as "Scan report submitted · Snyk · 2026-10-01 · 1.2.3". That is not a claim that the tool is safe, and it is not part of the agent-readiness score. See [Methodology](https://agentready-tools.com/methodology) and [Terms](https://agentready-tools.com/terms).
