chrome
AI agents invoke chrome to trigger actions in MCP Lite Wrappers. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Given the server context mentions Chrome DevTools integration, this tool likely controls a Chrome browser instance, enabling browser automation such as navigation, clicking, script execution, and DOM manipulation — all Execute-category actions with high blast radius. Confidence is moderate due to the empty description.
From the tool's definition Tool name is 'chrome' on a server that wraps Chrome DevTools; description is empty and uninformative.
Attacks that exploit this kind of access
chrome. It is categorised as a Execute tool in the MCP Lite Wrappers MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Lite Wrappers MCP server in PolicyLayer and add a rule for chrome: 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 Lite Wrappers. Nothing to install.
chrome is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the chrome 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. 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 is provided by the MCP Lite Wrappers MCP server (sbraind/mcp-lite-wrappers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
chrome is one line of MCP Lite Wrappers's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →