AI agents call search_articles to retrieve information from Inoreader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data (search operation) without creating, modifying, deleting, or executing code. The API endpoint is documented as stable for the purpose of searching and reading content. The blast radius of misuse is minimal—an agent could perform excessive queries against the service, but the rate limiting (1 Zone 1 request per page) mitigates resource exhaustion concerns.
From the tool's definition Tool performs search and retrieval of articles by keyword across feeds. Returns query results without modifying or deleting data.
Attacks that exploit this kind of access
Search for articles by keyword across all feeds. Costs 1 Zone 1 request per page. Uses undocumented but stable search endpoint. It is categorised as a Read tool in the Inoreader MCP Server, which means it retrieves data without modifying state.
Register the Inoreader MCP server in PolicyLayer and add a rule for search_articles: 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 Inoreader. Nothing to install.
search_articles 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 search_articles 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 search_articles. 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.
search_articles is provided by the Inoreader MCP server (justmytwospence/inoreader-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 →