AI agents use vote_witness to create or update resources in Tron — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tron environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
votes | array | Yes | List of SR addresses and vote counts |
network | string | — | Network name. Defaults to mainnet. |
Parameters from the server's own tool schema.
An AI agent can call vote_witness faster than any human can review — one bad instruction and it creates or modifies resources in Tron by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Vote for Super Representatives using TRON Power (obtained by freezing TRX). Each frozen TRX = 1 vote. It is categorised as a Write tool in the Tron MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
vote_witness accepts 2 parameters: votes, network. Required: votes. The full parameter table on this page comes from the server's own tool schema.
Register the Tron MCP server in PolicyLayer and add a rule for vote_witness: 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 Tron. Nothing to install.
vote_witness is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the vote_witness 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 vote_witness. 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.
vote_witness is provided by the Tron MCP server (@bankofai/mcp-server-tron). 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 →