AI-powered semantic search across browser tabs
AI agents call search_tabs_content 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 and queries tab content without creating, modifying, or deleting data. The semantic search capability is informational only, with no side effects. Blast radius is minimal—misuse results in reading unintended content from the user's browser tabs, not data destruction, code execution, or financial harm.
From the tool's definition The tool performs 'semantic search across browser tabs' with no modification capability indicated. The name and description align with retrieval operations (search, list).
Attacks that exploit this kind of access
AI-powered semantic search across browser tabs. 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 search_tabs_content: 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.
search_tabs_content 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_tabs_content 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_tabs_content. 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_tabs_content 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 →