AI agents call get_reading_highlights to retrieve information from Rewind without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves previously saved highlights and metadata from Instapaper articles. It performs a query operation that returns data without side effects. The verb 'Get' combined with the read-only nature of retrieving already-saved content clearly positions this as a Read category tool with low severity risk.
From the tool's definition Tool name is 'get_reading_highlights' and description states it 'Get[s] saved highlights' and 'Returns the highlighted text, notes, source article, and article URLs' — purely retrieval operations with no modification, deletion, or execution.
Attacks that exploit this kind of access
Get saved highlights from Instapaper articles. Returns the highlighted text, notes, source article, and article URLs as resource links. It is categorised as a Read tool in the Rewind MCP Server, which means it retrieves data without modifying state.
Register the Rewind MCP server in PolicyLayer and add a rule for get_reading_highlights: 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 Rewind. Nothing to install.
get_reading_highlights 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_reading_highlights 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_reading_highlights. 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_reading_highlights is provided by the Rewind MCP server (rewind-mcp-server). 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 →