# delete_model

Delete a downloaded model from the local node.

Agent View of the PolicyLayer registry record for `delete_model`. HTML page: https://policylayer.com/tools/network-tenzro-tenzro/delete-model

## Facts

- Tool: `delete_model`
- Server: Tenzro Ledger MCP (`https://canton-mcp.tenzro.network/mcp`) — https://policylayer.com/tools/network-tenzro-tenzro.md
- Homepage: https://github.com/tenzro/tenzro-network
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server auth posture: gated_ambiguous
- Server CORS policy: *
- 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": "delete_model",
    "arguments": {}
  }
}
```

## Why delete_model is rated Critical

This tool performs an irreversible deletion of data (a model stored on the node). Although the blast radius is somewhat contained to local node state rather than system-wide or financial impact, the destruction of a downloaded model cannot be undone and represents a clear destructive operation.

From the tool's own definition: "The tool name is 'delete_model' and the description states it will 'Delete a downloaded model from the local node.' The verb 'delete' is explicitly destructive, and removing a model is an irreversible operation that cannot be undone."

## Use case

AI agents call delete_model to permanently remove resources in Tenzro Ledger MCP, 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 Tenzro Ledger MCP:

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

## Other tools on Tenzro Ledger MCP (359)

- `clear_secure_mint_policy` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/clear-secure-mint-policy.md
- `deregister_agent` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/deregister-agent.md
- `drop_database` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/drop-database.md
- `forget_identity` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/forget-identity.md
- `freeze_address` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/freeze-address.md
- `revoke_did` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/revoke-did.md
- `revoke_session` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/revoke-session.md
- `secure_mint_record_burn` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/secure-mint-record-burn.md
- `urwa_clear_kill_switch` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/urwa-clear-kill-switch.md
- `urwa_trigger_kill_switch` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/urwa-trigger-kill-switch.md
- `x402_deregister_resource` — Destructive — https://policylayer.com/tools/network-tenzro-tenzro/x402-deregister-resource.md
- `assign_task` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/assign-task.md
- `axelar_call_contract` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/axelar-call-contract.md
- `babylon_submit_finality_signature` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/babylon-submit-finality-signature.md
- `canton_submit_command` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/canton-submit-command.md
- `chat_completion` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/chat-completion.md
- `chat_stream` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/chat-stream.md
- `create_swarm` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/create-swarm.md
- `database_query` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/database-query.md
- `deploy_contract` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/deploy-contract.md
- `derive_key` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/derive-key.md
- `download_model` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/download-model.md
- `encode_function` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/encode-function.md
- `encrypt_data` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/encrypt-data.md
- `hyperlane_dispatch` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/hyperlane-dispatch.md
- `moe_forward` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/moe-forward.md
- `rotate_validator_key` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/rotate-validator-key.md
- `send_agent_message` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/send-agent-message.md
- `set_secure_mint_paused` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/set-secure-mint-paused.md
- `sign_message` — Execute — https://policylayer.com/tools/network-tenzro-tenzro/sign-message.md
- …and 329 more: https://policylayer.com/tools/network-tenzro-tenzro.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=network-tenzro-tenzro · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/network-tenzro-tenzro