Plan a multi-step operation (transfer, swap, buy resources, etc) and return a cost estimate, total energy/bandwidth needed, and the cheapest resource acquisition strategy. NOTE: actual on-chain execution of multi-step intents is not yet wired up — currently returns the same plan as simulate, rega...
AI agents invoke execute_intent to trigger actions in MERX - TRON Resource Exchange. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool plans and coordinates multi-step operations that include transfers, swaps, and resource purchases on the TRON blockchain. Although the description notes actual execution is not yet implemented, the tool's design purpose is to orchestrate Execute-category operations (transfers, swaps) that modify on-chain state.
From the tool's definition Tool description states it 'Plan[s] a multi-step operation (transfer, swap, buy resources, etc)' and 'return[s]...the cheapest resource acquisition strategy.' The note clarifies that 'actual on-chain execution...is not yet wired up' but acknowledges the…
Attacks that exploit this kind of access
Plan a multi-step operation (transfer, swap, buy resources, etc) and return a cost estimate, total energy/bandwidth needed, and the cheapest resource acquisition strategy. NOTE: actual on-chain execution of multi-step intents is not yet wired up — currently returns the same plan as simulate, regardless of dry_run. Use this for planning; for real execution call the underlying tools (create_order, transfer_trc20, execute_swap) yourself in sequence. Auth required. It is categorised as a Execute tool in the MERX - TRON Resource Exchange MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MERX - TRON Resource Exchange MCP server in PolicyLayer and add a rule for execute_intent: 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 MERX - TRON Resource Exchange. Nothing to install.
execute_intent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_intent 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 execute_intent. 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.
execute_intent is provided by the MERX - TRON Resource Exchange MCP server (Hovsteder/merx-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 →