List bookmarks with optional filters. Supports hierarchical filtering via parentId.
AI agents call list_bookmarks to retrieve information from MCP Bookmarks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns bookmark data without modifying, deleting, or executing any operations. The 'list' operation is explicitly a read-only action. The optional filters and hierarchical filtering via parentId do not change the underlying data. Severity is low because the blast radius of misuse is minimal—an AI agent listing bookmarks cannot cause harm to the system or data.
From the tool's definition Tool name 'list_bookmarks' and description 'List bookmarks with optional filters' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List bookmarks with optional filters. Supports hierarchical filtering via parentId. It is categorised as a Read tool in the MCP Bookmarks MCP Server, which means it retrieves data without modifying state.
Register the MCP Bookmarks MCP server in PolicyLayer and add a rule for list_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 MCP Bookmarks. Nothing to install.
list_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 list_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 list_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.
list_bookmarks is provided by the MCP Bookmarks MCP server (linonon/mcpbookmarks). 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 →