Add new bookmarks with folder support
AI agents use chrome_bookmark_add to create or update resources in Chrome MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Chrome MCP Server environment.
Adding bookmarks creates or modifies browser state (the bookmark collection) but does not execute code, access sensitive data with read-like intent, delete data, or commit financial transactions. It is a standard Write operation with low severity since bookmarks are user preference data with minimal blast radius if misused by an AI agent—worst case being unwanted bookmarks added to the user's collection.
From the tool's definition Tool name 'chrome_bookmark_add' and description 'Add new bookmarks with folder support' indicate creation of new bookmark entries, a reversible write operation.
Attacks that exploit this kind of access
Add new bookmarks with folder support. It is categorised as a Write tool in the Chrome MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Chrome MCP Server MCP server in PolicyLayer and add a rule for chrome_bookmark_add: 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 Chrome MCP Server. Nothing to install.
chrome_bookmark_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the chrome_bookmark_add 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 chrome_bookmark_add. 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.
chrome_bookmark_add is provided by the Chrome MCP Server MCP server (mnisred/mcp-chrome). 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 →