admin-only
A tool restricted to admin role (RBAC roles.any)
This record as markdown: /tools/frontmcp/admin-only.md
What admin-only does on Frontmcp
AI agents invoke admin-only to trigger actions in Frontmcp. 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.
Why admin-only is rated High
The description does not specify the tool's actual action, only its access control restriction. Given the 'admin-only' designation and the context of sibling tools like 'admin_action' and 'admin-background-job', this tool likely performs privileged administrative operations. Without a clear description of the action, Execute is the most appropriate category given administrative tools typically trigger operations.
From the tool's definition 'A tool restricted to admin role (RBAC roles.any)' — the name 'admin-only' and admin-role restriction suggest privileged operations, but the description is uninformative about what the tool actually does.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs admin-only safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Frontmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For admin-only, this is the rule to start with:
admin-only stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Frontmcp, apply this rule, and every admin-only call is checked against it from then on.
Questions about admin-only
A tool restricted to admin role (RBAC roles.any). It is categorised as a Execute tool in the Frontmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Front MCP server in PolicyLayer and add a rule for admin-only: 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 Frontmcp. Nothing to install.
admin-only 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 admin-only 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 admin-only. 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.
admin-only is provided by the Front MCP server (agentfront/frontmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Front, and thousands of servers like it.
Across the catalogue