Get accumulated rewards information for a delegator. Shows current stake value (which includes auto-compounded rewards), optional reward calculation if original stake provided, and future reward estimates. NOTE: 0G Chain automatically compounds rewards into stake - there is NO separate claim func...
AI agents call get_accumulated_rewards to retrieve information from 0g Chain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_accumulated_rewards retrieves and queries reward information for a delegator without side effects. It calculates and displays values but does not create, modify, delete, or execute any operations.
From the tool's definition Tool description explicitly states 'Read-only operation' and the tool only 'Shows current stake value' and provides 'reward estimates' without modifying any data. No state changes occur.
Attacks that exploit this kind of access
Get accumulated rewards information for a delegator. Shows current stake value (which includes auto-compounded rewards), optional reward calculation if original stake provided, and future reward estimates. NOTE: 0G Chain automatically compounds rewards into stake - there is NO separate claim function! To receive rewards, use unstake_tokens. Read-only operation. It is categorised as a Read tool in the 0g Chain MCP Server, which means it retrieves data without modifying state.
Register the 0g Chain MCP server in PolicyLayer and add a rule for get_accumulated_rewards: 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.
get_accumulated_rewards is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_accumulated_rewards 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 get_accumulated_rewards. 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.
get_accumulated_rewards 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 →