AI agents call search_bookmarks to retrieve information from Raindrop Io MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations are read-only and retrieve data without side effects. The tool name and server context strongly suggest this queries bookmarks rather than modifying them. Blast radius if misused is low—an AI agent could perform unwanted searches but cannot harm data or perform financial transactions.
From the tool's definition Tool name 'search_bookmarks' indicates a search operation. No description provided, but in the context of Raindrop.io (a bookmark management service) and alongside sibling tools like 'add_bookmark' and 'search_by_tag', this tool retrieves/queries existing…
Documented attack patterns abuse exactly the kind of access search_bookmarks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Raindrop Io MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_bookmarks:
{
"version": "1",
"default": "deny",
"tools": {
"search_bookmarks": {}
}
}search_bookmarks 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.
search_bookmarks. It is categorised as a Read tool in the Raindrop Io MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Raindrop Io MCP Server MCP server in PolicyLayer and add a rule for search_bookmarks: 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 Raindrop Io MCP Server. Nothing to install.
search_bookmarks 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 search_bookmarks 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 search_bookmarks. 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.
search_bookmarks is provided by the Raindrop Io MCP Server MCP server (sachin-philip/raindrop.io-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Raindrop Io MCP Server, 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.
4 Raindrop Io MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.