Create a new admin access request on behalf of a user
AI agents use create_admin_access_request to create or update resources in BeyondTrust EPM MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BeyondTrust EPM MCP Server environment.
This tool creates a new admin access request, which is a Write operation (creating a record). However, the severity is high because admin access requests in a Privilege Management system, once approved, grant elevated privileges on endpoints.
From the tool's definition 'Create a new admin access request on behalf of a user'
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Create a new admin access request on behalf of a user. It is categorised as a Write tool in the BeyondTrust EPM MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the BeyondTrust EPM MCP Server MCP server in PolicyLayer and add a rule for create_admin_access_request: 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 BeyondTrust EPM MCP Server. Nothing to install.
create_admin_access_request 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 create_admin_access_request 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 create_admin_access_request. 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.
create_admin_access_request is provided by the BeyondTrust EPM MCP Server MCP server (wesharris222/btepmmcp). 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 →