Find bookmarks by keywords
AI agents call chrome_bookmark_search to retrieve information from Chrome MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/retrieval operation on existing bookmark data. It does not create, modify, delete, or execute any actions—it simply queries and returns matching bookmarks. This is a classic Read operation with minimal security risk, as it only provides access to metadata the user has already stored in their browser.
From the tool's definition Tool name 'chrome_bookmark_search' and description 'Find bookmarks by keywords' indicate a query operation that retrieves bookmark data without modification or side effects.
Attacks that exploit this kind of access
Find bookmarks by keywords. It is categorised as a Read tool in the Chrome MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Chrome MCP Server MCP server in PolicyLayer and add a rule for chrome_bookmark_search: 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_search 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 chrome_bookmark_search 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_search. 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_search is provided by the Chrome MCP Server MCP server (marie6789040106650/mcp-chrome-bk). 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 →