Get the RSS feed from TabNews.
AI agents call getRssFeedTool to retrieve information from MCP TabNews Integration without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches and returns RSS feed data from TabNews without modifying, executing, or deleting anything. It is a pure read operation that retrieves published content in a standard syndication format. The blast radius of misuse is minimal—an AI agent could retrieve excessive feeds or spam requests, but no data is modified or destroyed.
From the tool's definition Tool name 'getRssFeedTool' and description 'Get the RSS feed from TabNews' indicate a retrieval operation with no side effects. RSS feeds are public, read-only content.
Attacks that exploit this kind of access
Get the RSS feed from TabNews. It is categorised as a Read tool in the MCP TabNews Integration MCP Server, which means it retrieves data without modifying state.
Register the MCP TabNews Integration MCP server in PolicyLayer and add a rule for getRssFeedTool: 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 MCP TabNews Integration. Nothing to install.
getRssFeedTool 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 getRssFeedTool 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 getRssFeedTool. 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.
getRssFeedTool is provided by the MCP TabNews Integration MCP server (renant/mcp-tabnews). 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 →