rescreen_portfolio
PAID. Re-screen your own list of subjects against sanctions-list changes since a given date. Answers "which of MY clients were affected", which list_recent_updates cannot: that tool returns the global change feed, this one intersects it with your portfolio. Requires payment via x402; call without...
This record as markdown: /tools/dev-cz-agents-isir/rescreen-portfolio.md
What rescreen_portfolio does on Isir
AI agents call rescreen_portfolio to retrieve information from Isir 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 |
|---|---|---|---|
since | string | Yes | ISO date of the last screening, e.g. "2026-07-01". |
source | string | — | |
subjects | array | Yes | Up to 11 subjects per paid call (batch cap sized to the per-call price, not per-subject). Each needs at least a name or an ICO. |
Parameters from the server's own tool schema.
Why rescreen_portfolio is rated Low
The primary function is to retrieve and cross-reference data (screening a portfolio against sanctions changes), which is fundamentally a Read operation—querying and analyzing existing information. Although payment is required, the tool itself does not execute financial transactions; it merely gates access.
From the tool's definition Tool description states it 're-screen[s] your own list of subjects against sanctions-list changes' and 'intersects' a change feed with a portfolio to answer 'which of MY clients were affected'.
Attacks that exploit this kind of access
The rule that runs rescreen_portfolio safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Isir, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For rescreen_portfolio, this is the rule to start with:
rescreen_portfolio 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 Isir, apply this rule, and every rescreen_portfolio call is checked against it from then on.
Questions about rescreen_portfolio
PAID. Re-screen your own list of subjects against sanctions-list changes since a given date. Answers "which of MY clients were affected", which list_recent_updates cannot: that tool returns the global change feed, this one intersects it with your portfolio. Requires payment via x402; call without payment first to receive the terms. It is categorised as a Read tool in the Isir MCP Server, which means it retrieves data without modifying state.
rescreen_portfolio accepts 3 parameters: since, source, subjects. Required: since, subjects. The full parameter table on this page comes from the server's own tool schema.
Register the Isir MCP server in PolicyLayer and add a rule for rescreen_portfolio: 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 Isir. Nothing to install.
rescreen_portfolio 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 rescreen_portfolio 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 rescreen_portfolio. 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.
rescreen_portfolio is provided by the Isir MCP server (@czagents/isir). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Isir, and thousands of servers like it.
This server
Across the catalogue