get_readwise_highlights_by_filters
AI agents call get_readwise_highlights_by_filters to retrieve information from Kiseki-Labs-Readwise-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves highlights from Readwise based on filter criteria. The 'get' prefix and filter-based query pattern indicate a read-only operation that queries data without modification, deletion, or execution of arbitrary code. The empty description prevents higher confidence, but the naming convention and sibling context strongly suggest retrieval functionality.
From the tool's definition Tool name contains 'get_readwise_highlights_by_filters' which indicates data retrieval; sibling tools include 'get_readwise_highlights_by_document_ids' and 'list_readwise_documents_by_filters' which are clearly Read operations.
Documented attack patterns abuse exactly the kind of access get_readwise_highlights_by_filters gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kiseki-Labs-Readwise-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_readwise_highlights_by_filters:
{
"version": "1",
"default": "deny",
"tools": {
"get_readwise_highlights_by_filters": {}
}
} get_readwise_highlights_by_filters is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_readwise_highlights_by_filters. It is categorised as a Read tool in the Kiseki-Labs-Readwise-MCP MCP Server, which means it retrieves data without modifying state.
Register the Kiseki-Labs-Readwise- MCP server in PolicyLayer and add a rule for get_readwise_highlights_by_filters: 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 Kiseki-Labs-Readwise-MCP. Nothing to install.
get_readwise_highlights_by_filters 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_readwise_highlights_by_filters 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_readwise_highlights_by_filters. 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_readwise_highlights_by_filters is provided by the Kiseki-Labs-Readwise- MCP server (kiseki-technologies/kiseki-labs-readwise-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kiseki-Labs-Readwise-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Kiseki-Labs-Readwise-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.