# unstake_tokens

Unstake (undelegate) 0G tokens from a validator. Burns delegation shares and starts 21-day unbonding period. Tokens automatically sent to withdrawal address after unbonding. Requires withdrawal fee payment. Supports partial or full unstaking (

Agent View of the PolicyLayer registry record for `unstake_tokens`. HTML page: https://policylayer.com/tools/tairon-ai-0g-chain-mcp/unstake-tokens

## Facts

- Tool: `unstake_tokens`
- Server: 0g Chain (`tairon-ai/0g-chain-mcp`) — https://policylayer.com/tools/tairon-ai-0g-chain-mcp.md
- Homepage: https://github.com/Tairon-ai/0g-chain-mcp
- Risk category: Financial (Critical risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Approval-gated

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

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

## Why unstake_tokens is rated Critical

This tool commits a financial operation on a blockchain: it burns delegation shares, initiates an irreversible 21-day unbonding period, requires fee payment, and triggers automatic token transfer to a withdrawal address. It moves staked assets and commits financial obligations, placing it firmly in the Financial category. The irreversible unbonding period and fee payment raise severity to high.

From the tool's own definition: "Unstake (undelegate) 0G tokens from a validator. Burns delegation shares and starts 21-day unbonding period. Tokens automatically sent to withdrawal address after unbonding. Requires withdrawal fee payment."

## Use case

AI agents use unstake_tokens to commit financial operations through 0g Chain, 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 0g Chain:

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

## Other tools on 0g Chain (8)

- `send_native_token` — Financial — https://policylayer.com/tools/tairon-ai-0g-chain-mcp/send-native-token.md
- `stake_tokens` — Financial — https://policylayer.com/tools/tairon-ai-0g-chain-mcp/stake-tokens.md
- `get_accumulated_rewards` — Read — https://policylayer.com/tools/tairon-ai-0g-chain-mcp/get-accumulated-rewards.md
- `get_balance` — Read — https://policylayer.com/tools/tairon-ai-0g-chain-mcp/get-balance.md
- `get_staking_info` — Read — https://policylayer.com/tools/tairon-ai-0g-chain-mcp/get-staking-info.md
- `get_validator_info` — Read — https://policylayer.com/tools/tairon-ai-0g-chain-mcp/get-validator-info.md
- `get_validators_list` — Read — https://policylayer.com/tools/tairon-ai-0g-chain-mcp/get-validators-list.md
- `create_wallet` — Write — https://policylayer.com/tools/tairon-ai-0g-chain-mcp/create-wallet.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=tairon-ai-0g-chain-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/tairon-ai-0g-chain-mcp