# receive_attachment

Default first choice for Agent automatic attachment receiving. Takes only attachment_id; no path or overwrite input. Saves to downloads/ under this installed bridge package root (not cwd), created lazily on first receive; optional advanced MSG_DOWNLOAD_DIR must be an existing absolute directory. Always auto-names and never overwrites. Verifies SHA-256 before exclusive publication; returns actual path and hash. Saving does not mark read. Save successfully before reading the body; on failure ask retry, explicitly skip, or cancel. A successful result with cleanupWarning is still saved: report it, do not download again. Use save_attachment only for a user-specified destination. ${READING_GUIDANCE} ${UNTRUSTED}

Agent View of the PolicyLayer registry record for `receive_attachment`. HTML page: https://policylayer.com/tools/a2a-msg/receive-attachment

## Facts

- Tool: `receive_attachment`
- Server: A2a Msg (`goudaren0528/a2a-msg`) — https://policylayer.com/tools/a2a-msg.md
- Homepage: https://github.com/goudaren0528/a2a-msg
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Hidden

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

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

## Why receive_attachment is rated Critical

An AI agent that decides to call receive_attachment doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from A2a Msg is gone. There is no undo for destructive operations.

Risk signals: Admin/system-level operation

## Use case

AI agents call receive_attachment to permanently remove resources in A2a Msg, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches A2a Msg:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "receive_attachment"
  ]
}
```

## Other tools on A2a Msg (9)

- `get_unread_summary` — Read — https://policylayer.com/tools/a2a-msg/get-unread-summary.md
- `getmsg` — Read — https://policylayer.com/tools/a2a-msg/getmsg.md
- `list_peers` — Read — https://policylayer.com/tools/a2a-msg/list-peers.md
- `read_attachment_text` — Read — https://policylayer.com/tools/a2a-msg/read-attachment-text.md
- `read_message` — Read — https://policylayer.com/tools/a2a-msg/read-message.md
- `mark_read` — Write — https://policylayer.com/tools/a2a-msg/mark-read.md
- `save_attachment` — Write — https://policylayer.com/tools/a2a-msg/save-attachment.md
- `send_file` — Write — https://policylayer.com/tools/a2a-msg/send-file.md
- `send_message` — Write — https://policylayer.com/tools/a2a-msg/send-message.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=a2a-msg · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a2a-msg