infomaniak_audit_mailbox_security
Read-only admin audit for a mailbox security posture: spam policy, sender conflicts, Sieve scripts, and disabled filters.
This record as markdown: /tools/henrikogaard-infomaniak-admin-mcp/infomaniak-audit-mailbox-security.md
What infomaniak_audit_mailbox_security does on Infomaniak Admin
AI agents call infomaniak_audit_mailbox_security to retrieve information from Infomaniak Admin without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why infomaniak_audit_mailbox_security is rated Low
This is a read-only auditing tool that queries and retrieves security configuration data from mailbox accounts. While it accesses sensitive security information (spam policies, Sieve scripts, filter status), it has no capability to modify or execute actions—it only retrieves data for inspection.
From the tool's definition Tool is explicitly described as 'Read-only admin audit' that retrieves mailbox security information including 'spam policy, sender conflicts, Sieve scripts, and disabled filters.' No write, execute, or destructive capabilities mentioned.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs infomaniak_audit_mailbox_security safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Infomaniak Admin, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For infomaniak_audit_mailbox_security, this is the rule to start with:
infomaniak_audit_mailbox_security is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Infomaniak Admin, apply this rule, and every infomaniak_audit_mailbox_security call is checked against it from then on.
Questions about infomaniak_audit_mailbox_security
Read-only admin audit for a mailbox security posture: spam policy, sender conflicts, Sieve scripts, and disabled filters. It is categorised as a Read tool in the Infomaniak Admin MCP Server, which means it retrieves data without modifying state.
Register the Infomaniak Admin MCP server in PolicyLayer and add a rule for infomaniak_audit_mailbox_security: 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 Infomaniak Admin. Nothing to install.
infomaniak_audit_mailbox_security is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the infomaniak_audit_mailbox_security 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 infomaniak_audit_mailbox_security. 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.
infomaniak_audit_mailbox_security is provided by the Infomaniak Admin MCP server (henrikogaard/infomaniak-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Infomaniak Admin, and thousands of servers like it.
This server
Across the catalogue