Stake 0G tokens to a validator to earn rewards. Accepts either validator consensus public key (96 hex chars) OR validator EVM address (40 hex chars, from explorer). Delegates tokens through the 0G Chain staking contract. Returns transaction hash, validator info, estimated rewards (APY ~12.5%), an...
AI agents use stake_tokens to commit financial operations through 0g Chain — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool commits financial assets (tokens) to a blockchain staking contract, locking them with a 21-day unbonding period. This constitutes a financial obligation/commitment and is effectively irreversible in the short term.
From the tool's definition Stake 0G tokens to a validator to earn rewards... Delegates tokens through the 0G Chain staking contract. Returns transaction hash... Note: 21-day unbonding period applies.
Attacks that exploit this kind of access
Stake 0G tokens to a validator to earn rewards. Accepts either validator consensus public key (96 hex chars) OR validator EVM address (40 hex chars, from explorer). Delegates tokens through the 0G Chain staking contract. Returns transaction hash, validator info, estimated rewards (APY ~12.5%), and staking details. Note: 21-day unbonding period applies. It is categorised as a Financial tool in the 0g Chain MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the 0g Chain MCP server in PolicyLayer and add a rule for stake_tokens: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches 0g Chain. Nothing to install.
stake_tokens is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the stake_tokens rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for stake_tokens. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
stake_tokens is provided by the 0g Chain MCP server (tairon-ai/0g-chain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →