# release_number

Release a provisioned number back to the pool. Always call this when you are done with the session — even on error — to avoid consuming pool capacity unnecessarily.

Agent View of the PolicyLayer registry record for `release_number`. HTML page: https://policylayer.com/tools/dev-agentsim-mcp/release-number

## Facts

- Tool: `release_number`
- Server: Mcp (`https://mcp.agentsim.dev/mcp`) — https://policylayer.com/tools/dev-agentsim-mcp.md
- Homepage: https://github.com/agentsimdev/agentsim-mcp
- Risk category: Destructive (Critical risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Hidden

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `input` | object | yes |  |

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": "release_number",
    "arguments": {
      "input": {}
    }
  }
}
```

## Why release_number is rated Critical

Releasing a provisioned number is an irreversible action: once returned to the pool, the number is no longer associated with the agent's session and cannot be reclaimed. Any pending messages or OTP codes tied to that number would be lost. This constitutes an irreversible destruction of an allocated resource, placing it firmly in the Destructive category.

From the tool's own definition: "Release a provisioned number back to the pool — this permanently deallocates the provisioned mobile number, making it unavailable for further use in the current session and potentially losing any associated messages or OTP state."

## Use case

AI agents call release_number to permanently remove resources in 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 Mcp:

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

## Other tools on Mcp (4)

- `get_messages` — Read — https://policylayer.com/tools/dev-agentsim-mcp/get-messages.md
- `list_numbers` — Read — https://policylayer.com/tools/dev-agentsim-mcp/list-numbers.md
- `wait_for_otp` — Read — https://policylayer.com/tools/dev-agentsim-mcp/wait-for-otp.md
- `provision_number` — Write — https://policylayer.com/tools/dev-agentsim-mcp/provision-number.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-agentsim-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-agentsim-mcp