# upload_image

Upload an image to A3Plus CDN (Cloudflare R2) and get back a permanent URL. Use this when the image source is WAF-protected (server-side fetch returns 403) or when you have the image bytes locally. Pass EITHER base64 (raw base64 or data: URI) OR url (server fetches it). The returned image.url can be used as featuredImageUrl, in inlineImages, or directly in markdown — create/update article will not refetch it. Allowed formats: jpeg, png, webp, gif, avif (detected from magic bytes). Max 10 MB.

Agent View of the PolicyLayer registry record for `upload_image`. HTML page: https://policylayer.com/tools/a3plus-mcp/upload-image

## Facts

- Tool: `upload_image`
- Server: A3plus (`a3plus-mcp`) — https://policylayer.com/tools/a3plus-mcp.md
- Install: `npx -y a3plus-mcp`
- Homepage: https://www.npmjs.com/package/a3plus-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 3 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `url` | string | no | Public source URL to fetch server-side. Mutually exclusive with base64. |
| `base64` | string | no | Base64-encoded image bytes (data: URI prefix tolerated). Mutually exclusive with url. |
| `siteId` | string | yes | The A3Plus site ID this image belongs to. |

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": "upload_image",
    "arguments": {
      "siteId": "<siteId>"
    }
  }
}
```

## Why upload_image is rated Medium

An AI agent can call upload_image faster than any human can review: one bad instruction and it creates or modifies resources in A3plus by the hundred, each call as confident as the last.

Risk signals: Accepts URL/endpoint input (url)

## Use case

AI agents use upload_image to create or update resources in A3plus, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A3plus environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches A3plus:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "upload_image": {
      "limits": [
        {
          "counter": "upload_image_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on A3plus (60)

- `delete_article` — Destructive — https://policylayer.com/tools/a3plus-mcp/delete-article.md
- `delete_sites` — Destructive — https://policylayer.com/tools/a3plus-mcp/delete-sites.md
- `list_domains` — Destructive — https://policylayer.com/tools/a3plus-mcp/list-domains.md
- `remove_project_member` — Destructive — https://policylayer.com/tools/a3plus-mcp/remove-project-member.md
- `update_article` — Destructive — https://policylayer.com/tools/a3plus-mcp/update-article.md
- `retry_sites` — Execute — https://policylayer.com/tools/a3plus-mcp/retry-sites.md
- `transfer_sites` — Financial — https://policylayer.com/tools/a3plus-mcp/transfer-sites.md
- `audit_project_articles` — Read — https://policylayer.com/tools/a3plus-mcp/audit-project-articles.md
- `bind_domain` — Read — https://policylayer.com/tools/a3plus-mcp/bind-domain.md
- `bredgio_list_agents` — Read — https://policylayer.com/tools/a3plus-mcp/bredgio-list-agents.md
- `bredgio_logout` — Read — https://policylayer.com/tools/a3plus-mcp/bredgio-logout.md
- `bredgio_status` — Read — https://policylayer.com/tools/a3plus-mcp/bredgio-status.md
- `bredgio_task_status` — Read — https://policylayer.com/tools/a3plus-mcp/bredgio-task-status.md
- `get_article` — Read — https://policylayer.com/tools/a3plus-mcp/get-article.md
- `get_intake_schema` — Read — https://policylayer.com/tools/a3plus-mcp/get-intake-schema.md
- `get_pack` — Read — https://policylayer.com/tools/a3plus-mcp/get-pack.md
- `get_playbook` — Read — https://policylayer.com/tools/a3plus-mcp/get-playbook.md
- `get_project` — Read — https://policylayer.com/tools/a3plus-mcp/get-project.md
- `get_project_readiness` — Read — https://policylayer.com/tools/a3plus-mcp/get-project-readiness.md
- `get_site_brand` — Read — https://policylayer.com/tools/a3plus-mcp/get-site-brand.md
- `get_site_content` — Read — https://policylayer.com/tools/a3plus-mcp/get-site-content.md
- `get_site_faq` — Read — https://policylayer.com/tools/a3plus-mcp/get-site-faq.md
- `get_site_seo` — Read — https://policylayer.com/tools/a3plus-mcp/get-site-seo.md
- `get_static_pages` — Read — https://policylayer.com/tools/a3plus-mcp/get-static-pages.md
- `gsc_search_analytics` — Read — https://policylayer.com/tools/a3plus-mcp/gsc-search-analytics.md
- `gsc_site_detail` — Read — https://policylayer.com/tools/a3plus-mcp/gsc-site-detail.md
- `gsc_sites` — Read — https://policylayer.com/tools/a3plus-mcp/gsc-sites.md
- `gsc_zero_data_sites` — Read — https://policylayer.com/tools/a3plus-mcp/gsc-zero-data-sites.md
- `index_coverage_report` — Read — https://policylayer.com/tools/a3plus-mcp/index-coverage-report.md
- `list_articles` — Read — https://policylayer.com/tools/a3plus-mcp/list-articles.md
- …and 30 more: https://policylayer.com/tools/a3plus-mcp.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=a3plus-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a3plus-mcp