Create or reuse a cloud browser session using Scrapeless. Updates the active session.
AI agents invoke browser_create to trigger actions in Scrapeless. 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.
This tool launches or reattaches to a cloud browser session, which is an external operation that establishes a stateful execution environment. It falls under Execute because it triggers external infrastructure (cloud browser) and updates active session state. The blast radius is high since a misused session can be used for scraping, credential theft, or further browser actions via sibling tools.
From the tool's definition 'Create or reuse a cloud browser session' and 'Updates the active session' — initiates an external cloud browser process with ongoing state
Attacks that exploit this kind of access
Create or reuse a cloud browser session using Scrapeless. Updates the active session. It is categorised as a Execute tool in the Scrapeless MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scrapeless MCP server in PolicyLayer and add a rule for browser_create: 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 Scrapeless. Nothing to install.
browser_create 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 browser_create 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 browser_create. 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.
browser_create is provided by the Scrapeless MCP server (scrapeless-mcp-server). 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 →