Scan filesystem to build synced_ranges from existing documents
AI agents call readwise_init_ranges to retrieve information from Readwise MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool scans the filesystem and builds internal state (synced_ranges) from existing documents. This is primarily a read/scan operation. However, it does write internal state as a side effect (building synced_ranges), which could be considered a Write. Since the primary action is scanning/reading and the state-building is a derived initialization step with low blast radius, Read is the most appropriate category.
From the tool's definition Scan filesystem to build synced_ranges from existing documents
Attacks that exploit this kind of access
Scan filesystem to build synced_ranges from existing documents. It is categorised as a Read tool in the Readwise MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Readwise MCP Server MCP server in PolicyLayer and add a rule for readwise_init_ranges: 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 Readwise MCP Server. Nothing to install.
readwise_init_ranges 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 readwise_init_ranges 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 readwise_init_ranges. 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.
readwise_init_ranges is provided by the Readwise MCP Server MCP server (ngpestelos/readwise-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 →