Retourne les actualités pour une date donnée.
AI agents call get_articles_by_date to retrieve information from Boring News without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries news articles filtered by date. It performs a read-only operation with no capability to modify, delete, or execute external code. The blast radius of misuse is minimal—an agent could only fetch unwanted articles, not cause harm.
From the tool's definition Tool name 'get_articles_by_date' and description 'Retourne les actualités pour une date donnée' (Returns news for a given date) indicate retrieval of news data with no modification, deletion, or side effects.
Attacks that exploit this kind of access
Retourne les actualités pour une date donnée. It is categorised as a Read tool in the Boring News MCP Server, which means it retrieves data without modifying state.
Register the Boring News MCP server in PolicyLayer and add a rule for get_articles_by_date: 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 Boring News. Nothing to install.
get_articles_by_date 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_articles_by_date 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_articles_by_date. 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_articles_by_date is provided by the Boring News MCP server (oliviergg/boring-news-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 →