AI agents use select-account to create or update resources in Ms 365 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ms 365 environment.
This tool performs a state-changing operation that affects subsequent tool behavior by designating which Microsoft account context will be used for future operations. This is a Write operation because it modifies configuration state reversibly.
From the tool's definition The tool 'select-account' modifies state by setting a default account selection. While it does not create or delete accounts, it changes the application's configured state (which account is active/default), which is a reversible data modification.
Attacks that exploit this kind of access
Select a Microsoft account as the default. Accepts email address (e.g. user@outlook.com) or account ID. Use list-accounts to discover available accounts. It is categorised as a Write tool in the Ms 365 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ms 365 MCP server in PolicyLayer and add a rule for select-account: 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 Ms 365. Nothing to install.
select-account 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 select-account 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 select-account. 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.
select-account is provided by the Ms 365 MCP server (@softeria/ms-365-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 →