AI agents call read_tab_content to retrieve information from Mcp Chrome Tabs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns the textual content of an already-open browser tab. It performs no destructive, financial, or code-execution operations, and does not modify data. The operation is read-only with no side effects beyond information retrieval.
From the tool's definition Tool name is 'read_tab_content' and description states 'Get readable content from a tab' — these explicitly indicate retrieval with no modification or execution.
Documented attack patterns abuse exactly the kind of access read_tab_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Chrome Tabs, and nothing reaches the server without passing your rules. This is the rule we recommend for read_tab_content:
{
"version": "1",
"default": "deny",
"tools": {
"read_tab_content": {}
}
}read_tab_content is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get readable content from a tab in the user. It is categorised as a Read tool in the Mcp Chrome Tabs MCP Server, which means it retrieves data without modifying state.
Register the Mcp Chrome Tabs MCP server in PolicyLayer and add a rule for read_tab_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 Mcp Chrome Tabs. Nothing to install.
read_tab_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 read_tab_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 read_tab_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.
read_tab_content is provided by the Mcp Chrome Tabs MCP server (pokutuna/mcp-chrome-tabs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Mcp Chrome Tabs tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Mcp Chrome Tabs tools catalogued and risk-classified — across an index of 42,500+ MCP servers.