clicks_simulate_split
Preview how a USDC payment would be split for an agent: how much goes to wallet (liquid) and how much to DeFi yield.
This record as markdown: /tools/dev-bd37-clicks-protocol/clicks-simulate-split.md
What clicks_simulate_split does on Clicks Protocol
AI agents call clicks_simulate_split to retrieve information from Clicks Protocol without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
amount | string | — | Payment amount in USDC (e.g. "100" for 100 USDC) |
agent_address | string | — | Ethereum address of the AI agent |
Parameters from the server's own tool schema.
Why clicks_simulate_split is rated Low
This tool queries and returns a preview of a payment split calculation. It does not create, modify, delete, or execute any actual financial transactions. While it is DeFi-related, it performs no fund movement, no binding commitment, and no state change. Misuse by an agent would result in only viewing incorrect or misleading split scenarios, not financial loss or unauthorized transfers.
From the tool's definition Tool description explicitly states 'Preview' and 'simulate' — it computes a hypothetical split without executing actual payments or transfers.
Attacks that exploit this kind of access
The rule that runs clicks_simulate_split safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Clicks Protocol, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For clicks_simulate_split, this is the rule to start with:
clicks_simulate_split is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Clicks Protocol, apply this rule, and every clicks_simulate_split call is checked against it from then on.
Questions about clicks_simulate_split
Preview how a USDC payment would be split for an agent: how much goes to wallet (liquid) and how much to DeFi yield. It is categorised as a Read tool in the Clicks Protocol MCP Server, which means it retrieves data without modifying state.
clicks_simulate_split accepts 2 parameters: amount, agent_address. The full parameter table on this page comes from the server's own tool schema.
Register the Clicks Protocol MCP server in PolicyLayer and add a rule for clicks_simulate_split: 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 Clicks Protocol. Nothing to install.
clicks_simulate_split 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 clicks_simulate_split 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 clicks_simulate_split. 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.
clicks_simulate_split is provided by the Clicks Protocol MCP server (dev-bd37/clicks-protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Clicks Protocol, and thousands of servers like it.
This server
Across the catalogue