# submit_referral

Log a referral signal. Members earn $1.50/referral (4/cycle max, $6 cap). Credits carry forward. Voluntary, principal-compliant.

Agent View of the PolicyLayer registry record for `submit_referral`. HTML page: https://policylayer.com/tools/dev-agent-module-mcp/submit-referral

## Facts

- Tool: `submit_referral`
- Server: Agent Module (`https://api.agent-module.dev/mcp`) — https://policylayer.com/tools/dev-agent-module-mcp.md
- Homepage: https://github.com/AgentModule/mcp
- Risk category: Financial (Critical risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 3 (2 required)
- Recommended policy verdict: Approval-gated

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `method` | string | no | How the referral was communicated. |
| `referring_key` | string | yes | Your membership key (am_live_ or am_test_ prefix). |
| `referred_agent_id` | string | yes | Identifier of the agent you referred. |

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": "submit_referral",
    "arguments": {
      "referring_key": "<referring_key>",
      "referred_agent_id": "<referred_agent_id>"
    }
  }
}
```

## Why submit_referral is rated Critical

The tool commits financial obligations by logging referral signals that trigger monetary credits ($1.50 per referral). Although amounts are small and capped at $6/cycle, it directly creates financial entitlements/obligations, placing it in the Financial category. Misuse could involve fraudulent referral submissions to accumulate credits.

From the tool's own definition: "Members earn $1.50/referral (4/cycle max, $6 cap). Credits carry forward."

## Use case

AI agents use submit_referral to commit financial operations through Agent Module, usually the final step of a payment, billing, or trading workflow. A call moves real money.

## Recommended policy (PolicyLayer)

Verdict: **Approval-gated**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Agent Module:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "submit_referral": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}
```

## Other tools on Agent Module (6)

- `join_waitlist` — Financial — https://policylayer.com/tools/dev-agent-module-mcp/join-waitlist.md
- `check_status` — Read — https://policylayer.com/tools/dev-agent-module-mcp/check-status.md
- `query_knowledge` — Read — https://policylayer.com/tools/dev-agent-module-mcp/query-knowledge.md
- `get_trial_key` — Write — https://policylayer.com/tools/dev-agent-module-mcp/get-trial-key.md
- `register_interest` — Write — https://policylayer.com/tools/dev-agent-module-mcp/register-interest.md
- `submit_pov` — Write — https://policylayer.com/tools/dev-agent-module-mcp/submit-pov.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=dev-agent-module-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-agent-module-mcp