Search browser history with time filters
AI agents call chrome_history 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 retrieves historical browsing data from the browser without modifying, executing, or deleting anything. It is a simple search/query function analogous to 'get' or 'fetch' operations. The severity is low because leaked browsing history, while sensitive, does not enable direct financial harm, code execution, or data destruction.
From the tool's definition Tool name is 'chrome_history' and description states 'Search browser history with time filters' — both indicate a read-only query operation with no modification or execution capability.
Attacks that exploit this kind of access
Search browser history with time filters. 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_history: 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_history 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_history 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_history. 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_history is provided by the Chrome MCP Server MCP server (standbyme626/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 →