Get treasury bills auction results from Bank Al-Maghrib
AI agents call get_treasury_bills to retrieve information from Morocco Open Data MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves financial market data (treasury bills auction results) but does not execute trades, move money, or create financial obligations. It is a read operation on publicly available or semi-public financial data from Morocco's central bank.
From the tool's definition The tool is described as 'Get treasury bills auction results from Bank Al-Maghrib' — it retrieves historical auction data with no modification capability mentioned. The name and description use 'Get', indicating a read operation.
Attacks that exploit this kind of access
Get treasury bills auction results from Bank Al-Maghrib. It is categorised as a Read tool in the Morocco Open Data MCP MCP Server, which means it retrieves data without modifying state.
Register the Morocco Open Data MCP server in PolicyLayer and add a rule for get_treasury_bills: 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 Morocco Open Data MCP. Nothing to install.
get_treasury_bills 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 get_treasury_bills 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 get_treasury_bills. 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.
get_treasury_bills is provided by the Morocco Open Data MCP server (kcbdev/morocco-open-data-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 →