AI agents call iota_wallet_pending to retrieve information from Iota Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about pending transactions but does not execute, sign, modify, or delete any data. The listing of pending requests is a read-only operation with no destructive consequences. Even in a blockchain wallet context, merely viewing what requests are pending carries minimal risk compared to actually approving or executing those requests.
From the tool's definition The tool description states it 'List[s] pending signing requests awaiting approval,' which is purely a retrieval/query operation with no side effects. It reads the state of pending requests without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access iota_wallet_pending gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Iota Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for iota_wallet_pending:
{
"version": "1",
"default": "deny",
"tools": {
"iota_wallet_pending": {}
}
}iota_wallet_pending is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List pending signing requests awaiting approval. It is categorised as a Read tool in the Iota Agent MCP Server, which means it retrieves data without modifying state.
Register the Iota Agent MCP server in PolicyLayer and add a rule for iota_wallet_pending: 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 Iota Agent. Nothing to install.
iota_wallet_pending 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 iota_wallet_pending 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 iota_wallet_pending. 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.
iota_wallet_pending is provided by the Iota Agent MCP server (scottcjn/iota-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 Iota Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 Iota Agent tools catalogued and risk-classified — across an index of 42,500+ MCP servers.