risk_check
Paid ($5 USDC on Algorand). Call BEFORE paying or hiring another agent: an ALLOW / WARN / DENY verdict on the counterparty with the reasons and signals behind it. Do not pay on DENY. Prefer check_before_pay. Saved for 24 hours: asking again returns the saved answer and pays nothing.
This record as markdown: /tools/a-identity-trust-mcp/risk-check.md
What risk_check does on Trust
AI agents call risk_check to retrieve information from Trust 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 |
|---|---|---|---|
agentId | string | Yes | The agent to check: an ERC-8004 token id ("#849980"), a CAIP id, or an owner address. |
amountUsd | number | — | What the payment you are about to make is worth, in USD. Sizes the verdict to the deal. |
Parameters from the server's own tool schema.
Why risk_check is rated Low
Even though risk_check only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs risk_check safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Trust, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For risk_check, this is the rule to start with:
risk_check 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 Trust, apply this rule, and every risk_check call is checked against it from then on.
Questions about risk_check
Paid ($5 USDC on Algorand). Call BEFORE paying or hiring another agent: an ALLOW / WARN / DENY verdict on the counterparty with the reasons and signals behind it. Do not pay on DENY. Prefer check_before_pay. Saved for 24 hours: asking again returns the saved answer and pays nothing. It is categorised as a Read tool in the Trust MCP Server, which means it retrieves data without modifying state.
risk_check accepts 2 parameters: agentId, amountUsd. Required: agentId. The full parameter table on this page comes from the server's own tool schema.
Register the Trust MCP server in PolicyLayer and add a rule for risk_check: 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 Trust. Nothing to install.
risk_check 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 risk_check 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 risk_check. 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.
risk_check is provided by the Trust MCP server (@a-identity/trust-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Trust, and thousands of servers like it.
This server
Across the catalogue