Get full content of an entry (auto-marks as read).
AI agents call read_entry_tool to retrieve information from MCP Feed Reader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The primary function is to retrieve and display the full content of a feed entry. While the tool auto-marks entries as read (a state change), this is a reversible, non-destructive metadata update that is incidental to the read operation and does not alter or remove data. The tool poses minimal risk if misused by an AI agent—it only accesses existing feed content.
From the tool's definition Tool name contains 'read_entry' and description states 'Get full content of an entry (auto-marks as read)'. This retrieves data without modifying the underlying entry content or creating destructive side effects.
Attacks that exploit this kind of access
Get full content of an entry (auto-marks as read). It is categorised as a Read tool in the MCP Feed Reader MCP Server, which means it retrieves data without modifying state.
Register the MCP Feed Reader MCP server in PolicyLayer and add a rule for read_entry_tool: 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 Feed Reader. Nothing to install.
read_entry_tool 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 read_entry_tool 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 read_entry_tool. 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.
read_entry_tool is provided by the MCP Feed Reader MCP server (pypi:mcp-feed-reader-crunchtools). 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 →