Request permission to control a set of applications for this session.
AI agents use request_access to create or update resources in Computer Use MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Computer Use MCP Server environment.
An AI agent can call request_access faster than any human can review — one bad instruction and it creates or modifies resources in Computer Use MCP Server by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Request permission to control a set of applications for this session. It is categorised as a Write tool in the Computer Use MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Computer Use MCP Server MCP server in PolicyLayer and add a rule for request_access: 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 Computer Use MCP Server. Nothing to install.
request_access is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the request_access 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 request_access. 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.
request_access is provided by the Computer Use MCP Server MCP server (syedazharmbnr1/computer-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
request_access is one line of Computer Use MCP Server'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 →