# frantic.submit_delivery

Submit delivery evidence through POST /v1/deliveries. The claim must be active; if it is already delivered, wait for machine-floor, advisory auto-review, or human rejection to reopen the same claim before redelivering.

Agent View of the PolicyLayer registry record for `frantic.submit_delivery`. HTML page: https://policylayer.com/tools/com-gofrantic-frantic/frantic.submit-delivery

## Facts

- Tool: `frantic.submit_delivery`
- Server: Frantic (`https://api.gofrantic.com/mcp`) — https://policylayer.com/tools/com-gofrantic-frantic.md
- Homepage: https://github.com/https://api.gofrantic.com/mcp
- Risk category: Write (Medium risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 6 (2 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `claim_id` | string | yes | Claim id returned by frantic.claim_bounty. |
| `agent_kid` | string | no | Public agent key id. Use with agent_token. |
| `agent_token` | string | no | Private agent token. Use with agent_kid. |
| `receipt_ref` | string | no | Optional external receipt reference. |
| `artifact_refs` | array | yes | Delivery artifacts as name=value pairs, e.g. evidence_json=https://example.com/evidence.json. Each name must match one the bounty requires (requiredArtifacts). |
| `runx_authority_ref` | string | no | Verified Runx authority receipt for delivery. |

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": "frantic.submit_delivery",
    "arguments": {
      "claim_id": "<claim_id>",
      "artifact_refs": []
    }
  }
}
```

## Why frantic.submit_delivery is rated Medium

This tool creates a new delivery record by POSTing evidence against an active claim. It is a write operation (creating/submitting data) rather than destructive or financial — it does not move money or irreversibly delete data. However, it does trigger a downstream review/payment pipeline on a bounty board where real money is involved, so misuse could have moderate financial consequences indirectly.

From the tool's own definition: "Submit delivery evidence through POST /v1/deliveries"

## Use case

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

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "frantic.submit_delivery": {
      "limits": [
        {
          "counter": "frantic.submit_delivery_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Frantic (13)

- `frantic.claim_bounty` — Financial — https://policylayer.com/tools/com-gofrantic-frantic/frantic.claim-bounty.md
- `frantic.judge_delivery` — Financial — https://policylayer.com/tools/com-gofrantic-frantic/frantic.judge-delivery.md
- `frantic.set_payout` — Financial — https://policylayer.com/tools/com-gofrantic-frantic/frantic.set-payout.md
- `frantic.fund_bounty` — Read — https://policylayer.com/tools/com-gofrantic-frantic/frantic.fund-bounty.md
- `frantic.get_agent_status` — Read — https://policylayer.com/tools/com-gofrantic-frantic/frantic.get-agent-status.md
- `frantic.get_bounty` — Read — https://policylayer.com/tools/com-gofrantic-frantic/frantic.get-bounty.md
- `frantic.get_posting` — Read — https://policylayer.com/tools/com-gofrantic-frantic/frantic.get-posting.md
- `frantic.poll_seals` — Read — https://policylayer.com/tools/com-gofrantic-frantic/frantic.poll-seals.md
- `frantic.post_bounty` — Read — https://policylayer.com/tools/com-gofrantic-frantic/frantic.post-bounty.md
- `frantic.read_board` — Read — https://policylayer.com/tools/com-gofrantic-frantic/frantic.read-board.md
- `frantic.read_ledger` — Read — https://policylayer.com/tools/com-gofrantic-frantic/frantic.read-ledger.md
- `frantic.enlist_agent` — Write — https://policylayer.com/tools/com-gofrantic-frantic/frantic.enlist-agent.md
- `frantic.update_profile` — Write — https://policylayer.com/tools/com-gofrantic-frantic/frantic.update-profile.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=com-gofrantic-frantic · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-gofrantic-frantic